Spaces:
Build error
Build error
Upload 25 files
Browse files- diffusion_webui/__init__.py +1 -0
- diffusion_webui/diffusion_models/__init__.py +0 -0
- diffusion_webui/diffusion_models/controlnet/__init__.py +0 -0
- diffusion_webui/diffusion_models/controlnet/controlnet_canny.py +183 -0
- diffusion_webui/diffusion_models/controlnet/controlnet_depth.py +187 -0
- diffusion_webui/diffusion_models/controlnet/controlnet_hed.py +181 -0
- diffusion_webui/diffusion_models/controlnet/controlnet_inpaint/__init__.py +0 -0
- diffusion_webui/diffusion_models/controlnet/controlnet_inpaint/controlnet_inpaint_app.py +203 -0
- diffusion_webui/diffusion_models/controlnet/controlnet_inpaint/pipeline_stable_diffusion_controlnet_inpaint.py +607 -0
- diffusion_webui/diffusion_models/controlnet/controlnet_mlsd.py +173 -0
- diffusion_webui/diffusion_models/controlnet/controlnet_pose.py +189 -0
- diffusion_webui/diffusion_models/controlnet/controlnet_scribble.py +188 -0
- diffusion_webui/diffusion_models/controlnet/controlnet_seg.py +353 -0
- diffusion_webui/diffusion_models/stable_diffusion/__init__.py +0 -0
- diffusion_webui/diffusion_models/stable_diffusion/__pycache__/__init__.cpython-38.pyc +0 -0
- diffusion_webui/diffusion_models/stable_diffusion/__pycache__/img2img_app.cpython-38.pyc +0 -0
- diffusion_webui/diffusion_models/stable_diffusion/__pycache__/inpaint_app.cpython-38.pyc +0 -0
- diffusion_webui/diffusion_models/stable_diffusion/__pycache__/text2img_app.cpython-38.pyc +0 -0
- diffusion_webui/diffusion_models/stable_diffusion/img2img_app.py +153 -0
- diffusion_webui/diffusion_models/stable_diffusion/inpaint_app.py +148 -0
- diffusion_webui/diffusion_models/stable_diffusion/text2img_app.py +170 -0
- diffusion_webui/helpers.py +33 -0
- diffusion_webui/utils/__init__.py +0 -0
- diffusion_webui/utils/model_list.py +33 -0
- diffusion_webui/utils/scheduler_list.py +47 -0
diffusion_webui/__init__.py
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
__version__ = "1.4.1"
|
diffusion_webui/diffusion_models/__init__.py
ADDED
File without changes
|
diffusion_webui/diffusion_models/controlnet/__init__.py
ADDED
File without changes
|
diffusion_webui/diffusion_models/controlnet/controlnet_canny.py
ADDED
@@ -0,0 +1,183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import cv2
|
2 |
+
import gradio as gr
|
3 |
+
import numpy as np
|
4 |
+
import torch
|
5 |
+
from diffusers import ControlNetModel, StableDiffusionControlNetPipeline
|
6 |
+
from PIL import Image
|
7 |
+
|
8 |
+
from diffusion_webui.utils.model_list import (
|
9 |
+
controlnet_canny_model_list,
|
10 |
+
stable_model_list,
|
11 |
+
)
|
12 |
+
from diffusion_webui.utils.scheduler_list import (
|
13 |
+
SCHEDULER_LIST,
|
14 |
+
get_scheduler_list,
|
15 |
+
)
|
16 |
+
|
17 |
+
|
18 |
+
class StableDiffusionControlNetCannyGenerator:
|
19 |
+
def __init__(self):
|
20 |
+
self.pipe = None
|
21 |
+
|
22 |
+
def load_model(self, stable_model_path, controlnet_model_path, scheduler):
|
23 |
+
if self.pipe is None:
|
24 |
+
controlnet = ControlNetModel.from_pretrained(
|
25 |
+
controlnet_model_path, torch_dtype=torch.float16
|
26 |
+
)
|
27 |
+
self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
|
28 |
+
pretrained_model_name_or_path=stable_model_path,
|
29 |
+
controlnet=controlnet,
|
30 |
+
safety_checker=None,
|
31 |
+
torch_dtype=torch.float16,
|
32 |
+
)
|
33 |
+
|
34 |
+
self.pipe = get_scheduler_list(pipe=self.pipe, scheduler=scheduler)
|
35 |
+
self.pipe.to("cuda")
|
36 |
+
self.pipe.enable_xformers_memory_efficient_attention()
|
37 |
+
|
38 |
+
return self.pipe
|
39 |
+
|
40 |
+
def controlnet_canny(
|
41 |
+
self,
|
42 |
+
image_path: str,
|
43 |
+
):
|
44 |
+
image = Image.open(image_path)
|
45 |
+
image = np.array(image)
|
46 |
+
|
47 |
+
image = cv2.Canny(image, 100, 200)
|
48 |
+
image = image[:, :, None]
|
49 |
+
image = np.concatenate([image, image, image], axis=2)
|
50 |
+
image = Image.fromarray(image)
|
51 |
+
|
52 |
+
return image
|
53 |
+
|
54 |
+
def generate_image(
|
55 |
+
self,
|
56 |
+
image_path: str,
|
57 |
+
stable_model_path: str,
|
58 |
+
controlnet_model_path: str,
|
59 |
+
prompt: str,
|
60 |
+
negative_prompt: str,
|
61 |
+
num_images_per_prompt: int,
|
62 |
+
guidance_scale: int,
|
63 |
+
num_inference_step: int,
|
64 |
+
scheduler: str,
|
65 |
+
seed_generator: int,
|
66 |
+
):
|
67 |
+
pipe = self.load_model(
|
68 |
+
stable_model_path=stable_model_path,
|
69 |
+
controlnet_model_path=controlnet_model_path,
|
70 |
+
scheduler=scheduler,
|
71 |
+
)
|
72 |
+
|
73 |
+
image = self.controlnet_canny(image_path=image_path)
|
74 |
+
|
75 |
+
if seed_generator == 0:
|
76 |
+
random_seed = torch.randint(0, 1000000, (1,))
|
77 |
+
generator = torch.manual_seed(random_seed)
|
78 |
+
else:
|
79 |
+
generator = torch.manual_seed(seed_generator)
|
80 |
+
|
81 |
+
output = pipe(
|
82 |
+
prompt=prompt,
|
83 |
+
image=image,
|
84 |
+
negative_prompt=negative_prompt,
|
85 |
+
num_images_per_prompt=num_images_per_prompt,
|
86 |
+
num_inference_steps=num_inference_step,
|
87 |
+
guidance_scale=guidance_scale,
|
88 |
+
generator=generator,
|
89 |
+
).images
|
90 |
+
|
91 |
+
return output
|
92 |
+
|
93 |
+
def app():
|
94 |
+
with gr.Blocks():
|
95 |
+
with gr.Row():
|
96 |
+
with gr.Column():
|
97 |
+
controlnet_canny_image_file = gr.Image(
|
98 |
+
type="filepath", label="Image"
|
99 |
+
)
|
100 |
+
|
101 |
+
controlnet_canny_prompt = gr.Textbox(
|
102 |
+
lines=1,
|
103 |
+
placeholder="Prompt",
|
104 |
+
show_label=False,
|
105 |
+
)
|
106 |
+
|
107 |
+
controlnet_canny_negative_prompt = gr.Textbox(
|
108 |
+
lines=1,
|
109 |
+
placeholder="Negative Prompt",
|
110 |
+
show_label=False,
|
111 |
+
)
|
112 |
+
with gr.Row():
|
113 |
+
with gr.Column():
|
114 |
+
controlnet_canny_stable_model_id = gr.Dropdown(
|
115 |
+
choices=stable_model_list,
|
116 |
+
value=stable_model_list[0],
|
117 |
+
label="Stable Model Id",
|
118 |
+
)
|
119 |
+
|
120 |
+
controlnet_canny_guidance_scale = gr.Slider(
|
121 |
+
minimum=0.1,
|
122 |
+
maximum=15,
|
123 |
+
step=0.1,
|
124 |
+
value=7.5,
|
125 |
+
label="Guidance Scale",
|
126 |
+
)
|
127 |
+
controlnet_canny_num_inference_step = gr.Slider(
|
128 |
+
minimum=1,
|
129 |
+
maximum=100,
|
130 |
+
step=1,
|
131 |
+
value=50,
|
132 |
+
label="Num Inference Step",
|
133 |
+
)
|
134 |
+
controlnet_canny_num_images_per_prompt = gr.Slider(
|
135 |
+
minimum=1,
|
136 |
+
maximum=10,
|
137 |
+
step=1,
|
138 |
+
value=1,
|
139 |
+
label="Number Of Images",
|
140 |
+
)
|
141 |
+
with gr.Row():
|
142 |
+
with gr.Column():
|
143 |
+
controlnet_canny_model_id = gr.Dropdown(
|
144 |
+
choices=controlnet_canny_model_list,
|
145 |
+
value=controlnet_canny_model_list[0],
|
146 |
+
label="ControlNet Model Id",
|
147 |
+
)
|
148 |
+
|
149 |
+
controlnet_canny_scheduler = gr.Dropdown(
|
150 |
+
choices=SCHEDULER_LIST,
|
151 |
+
value=SCHEDULER_LIST[0],
|
152 |
+
label="Scheduler",
|
153 |
+
)
|
154 |
+
|
155 |
+
controlnet_canny_seed_generator = gr.Number(
|
156 |
+
value=0,
|
157 |
+
label="Seed Generator",
|
158 |
+
)
|
159 |
+
controlnet_canny_predict = gr.Button(value="Generator")
|
160 |
+
|
161 |
+
with gr.Column():
|
162 |
+
output_image = gr.Gallery(
|
163 |
+
label="Generated images",
|
164 |
+
show_label=False,
|
165 |
+
elem_id="gallery",
|
166 |
+
).style(grid=(1, 2))
|
167 |
+
|
168 |
+
controlnet_canny_predict.click(
|
169 |
+
fn=StableDiffusionControlNetCannyGenerator().generate_image,
|
170 |
+
inputs=[
|
171 |
+
controlnet_canny_image_file,
|
172 |
+
controlnet_canny_stable_model_id,
|
173 |
+
controlnet_canny_model_id,
|
174 |
+
controlnet_canny_prompt,
|
175 |
+
controlnet_canny_negative_prompt,
|
176 |
+
controlnet_canny_num_images_per_prompt,
|
177 |
+
controlnet_canny_guidance_scale,
|
178 |
+
controlnet_canny_num_inference_step,
|
179 |
+
controlnet_canny_scheduler,
|
180 |
+
controlnet_canny_seed_generator,
|
181 |
+
],
|
182 |
+
outputs=[output_image],
|
183 |
+
)
|
diffusion_webui/diffusion_models/controlnet/controlnet_depth.py
ADDED
@@ -0,0 +1,187 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
import numpy as np
|
3 |
+
import torch
|
4 |
+
from diffusers import ControlNetModel, StableDiffusionControlNetPipeline
|
5 |
+
from PIL import Image
|
6 |
+
from transformers import pipeline
|
7 |
+
|
8 |
+
from diffusion_webui.utils.model_list import (
|
9 |
+
controlnet_depth_model_list,
|
10 |
+
stable_model_list,
|
11 |
+
)
|
12 |
+
from diffusion_webui.utils.scheduler_list import (
|
13 |
+
SCHEDULER_LIST,
|
14 |
+
get_scheduler_list,
|
15 |
+
)
|
16 |
+
|
17 |
+
|
18 |
+
class StableDiffusionControlNetDepthGenerator:
|
19 |
+
def __init__(self):
|
20 |
+
self.pipe = None
|
21 |
+
|
22 |
+
def load_model(self, stable_model_path, controlnet_model_path, scheduler):
|
23 |
+
if self.pipe is None:
|
24 |
+
controlnet = ControlNetModel.from_pretrained(
|
25 |
+
controlnet_model_path, torch_dtype=torch.float16
|
26 |
+
)
|
27 |
+
|
28 |
+
self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
|
29 |
+
pretrained_model_name_or_path=stable_model_path,
|
30 |
+
controlnet=controlnet,
|
31 |
+
safety_checker=None,
|
32 |
+
torch_dtype=torch.float16,
|
33 |
+
)
|
34 |
+
|
35 |
+
self.pipe = get_scheduler_list(pipe=self.pipe, scheduler=scheduler)
|
36 |
+
self.pipe.to("cuda")
|
37 |
+
self.pipe.enable_xformers_memory_efficient_attention()
|
38 |
+
|
39 |
+
return self.pipe
|
40 |
+
|
41 |
+
def controlnet_depth(self, image_path: str):
|
42 |
+
depth_estimator = pipeline("depth-estimation")
|
43 |
+
image = Image.open(image_path)
|
44 |
+
image = depth_estimator(image)["depth"]
|
45 |
+
image = np.array(image)
|
46 |
+
image = image[:, :, None]
|
47 |
+
image = np.concatenate([image, image, image], axis=2)
|
48 |
+
image = Image.fromarray(image)
|
49 |
+
|
50 |
+
return image
|
51 |
+
|
52 |
+
def generate_image(
|
53 |
+
self,
|
54 |
+
image_path: str,
|
55 |
+
stable_model_path: str,
|
56 |
+
depth_model_path: str,
|
57 |
+
prompt: str,
|
58 |
+
negative_prompt: str,
|
59 |
+
num_images_per_prompt: int,
|
60 |
+
guidance_scale: int,
|
61 |
+
num_inference_step: int,
|
62 |
+
scheduler: str,
|
63 |
+
seed_generator: int,
|
64 |
+
):
|
65 |
+
image = self.controlnet_depth(image_path)
|
66 |
+
|
67 |
+
pipe = self.load_model(
|
68 |
+
stable_model_path=stable_model_path,
|
69 |
+
controlnet_model_path=depth_model_path,
|
70 |
+
scheduler=scheduler,
|
71 |
+
)
|
72 |
+
|
73 |
+
if seed_generator == 0:
|
74 |
+
random_seed = torch.randint(0, 1000000, (1,))
|
75 |
+
generator = torch.manual_seed(random_seed)
|
76 |
+
else:
|
77 |
+
generator = torch.manual_seed(seed_generator)
|
78 |
+
|
79 |
+
output = pipe(
|
80 |
+
prompt=prompt,
|
81 |
+
image=image,
|
82 |
+
negative_prompt=negative_prompt,
|
83 |
+
num_images_per_prompt=num_images_per_prompt,
|
84 |
+
num_inference_steps=num_inference_step,
|
85 |
+
guidance_scale=guidance_scale,
|
86 |
+
generator=generator,
|
87 |
+
).images
|
88 |
+
|
89 |
+
return output
|
90 |
+
|
91 |
+
def app():
|
92 |
+
with gr.Blocks():
|
93 |
+
with gr.Row():
|
94 |
+
with gr.Column():
|
95 |
+
controlnet_depth_image_file = gr.Image(
|
96 |
+
type="filepath", label="Image"
|
97 |
+
)
|
98 |
+
|
99 |
+
controlnet_depth_prompt = gr.Textbox(
|
100 |
+
lines=1,
|
101 |
+
show_label=False,
|
102 |
+
placeholder="Prompt",
|
103 |
+
)
|
104 |
+
|
105 |
+
controlnet_depth_negative_prompt = gr.Textbox(
|
106 |
+
lines=1,
|
107 |
+
show_label=False,
|
108 |
+
placeholder="Negative Prompt",
|
109 |
+
)
|
110 |
+
|
111 |
+
with gr.Row():
|
112 |
+
with gr.Column():
|
113 |
+
controlnet_depth_stable_model_id = gr.Dropdown(
|
114 |
+
choices=stable_model_list,
|
115 |
+
value=stable_model_list[0],
|
116 |
+
label="Stable Model Id",
|
117 |
+
)
|
118 |
+
controlnet_depth_guidance_scale = gr.Slider(
|
119 |
+
minimum=0.1,
|
120 |
+
maximum=15,
|
121 |
+
step=0.1,
|
122 |
+
value=7.5,
|
123 |
+
label="Guidance Scale",
|
124 |
+
)
|
125 |
+
|
126 |
+
controlnet_depth_num_inference_step = gr.Slider(
|
127 |
+
minimum=1,
|
128 |
+
maximum=100,
|
129 |
+
step=1,
|
130 |
+
value=50,
|
131 |
+
label="Num Inference Step",
|
132 |
+
)
|
133 |
+
|
134 |
+
controlnet_depth_num_images_per_prompt = gr.Slider(
|
135 |
+
minimum=1,
|
136 |
+
maximum=10,
|
137 |
+
step=1,
|
138 |
+
value=1,
|
139 |
+
label="Number Of Images",
|
140 |
+
)
|
141 |
+
with gr.Row():
|
142 |
+
with gr.Column():
|
143 |
+
controlnet_depth_model_id = gr.Dropdown(
|
144 |
+
choices=controlnet_depth_model_list,
|
145 |
+
value=controlnet_depth_model_list[0],
|
146 |
+
label="ControlNet Model Id",
|
147 |
+
)
|
148 |
+
|
149 |
+
controlnet_depth_scheduler = gr.Dropdown(
|
150 |
+
choices=SCHEDULER_LIST,
|
151 |
+
value=SCHEDULER_LIST[0],
|
152 |
+
label="Scheduler",
|
153 |
+
)
|
154 |
+
|
155 |
+
controlnet_depth_seed_generator = gr.Number(
|
156 |
+
minimum=0,
|
157 |
+
maximum=1000000,
|
158 |
+
step=1,
|
159 |
+
value=0,
|
160 |
+
label="Seed Generator",
|
161 |
+
)
|
162 |
+
|
163 |
+
controlnet_depth_predict = gr.Button(value="Generator")
|
164 |
+
|
165 |
+
with gr.Column():
|
166 |
+
output_image = gr.Gallery(
|
167 |
+
label="Generated images",
|
168 |
+
show_label=False,
|
169 |
+
elem_id="gallery",
|
170 |
+
).style(grid=(1, 2))
|
171 |
+
|
172 |
+
controlnet_depth_predict.click(
|
173 |
+
fn=StableDiffusionControlNetDepthGenerator().generate_image,
|
174 |
+
inputs=[
|
175 |
+
controlnet_depth_image_file,
|
176 |
+
controlnet_depth_stable_model_id,
|
177 |
+
controlnet_depth_model_id,
|
178 |
+
controlnet_depth_prompt,
|
179 |
+
controlnet_depth_negative_prompt,
|
180 |
+
controlnet_depth_num_images_per_prompt,
|
181 |
+
controlnet_depth_guidance_scale,
|
182 |
+
controlnet_depth_num_inference_step,
|
183 |
+
controlnet_depth_scheduler,
|
184 |
+
controlnet_depth_seed_generator,
|
185 |
+
],
|
186 |
+
outputs=output_image,
|
187 |
+
)
|
diffusion_webui/diffusion_models/controlnet/controlnet_hed.py
ADDED
@@ -0,0 +1,181 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
import torch
|
3 |
+
from controlnet_aux import HEDdetector
|
4 |
+
from diffusers import ControlNetModel, StableDiffusionControlNetPipeline
|
5 |
+
from PIL import Image
|
6 |
+
|
7 |
+
from diffusion_webui.utils.model_list import (
|
8 |
+
controlnet_hed_model_list,
|
9 |
+
stable_model_list,
|
10 |
+
)
|
11 |
+
from diffusion_webui.utils.scheduler_list import (
|
12 |
+
SCHEDULER_LIST,
|
13 |
+
get_scheduler_list,
|
14 |
+
)
|
15 |
+
|
16 |
+
|
17 |
+
class StableDiffusionControlNetHEDGenerator:
|
18 |
+
def __init__(self):
|
19 |
+
self.pipe = None
|
20 |
+
|
21 |
+
def load_model(self, stable_model_path, controlnet_model_path, scheduler):
|
22 |
+
if self.pipe is None:
|
23 |
+
controlnet = ControlNetModel.from_pretrained(
|
24 |
+
controlnet_model_path, torch_dtype=torch.float16
|
25 |
+
)
|
26 |
+
|
27 |
+
self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
|
28 |
+
pretrained_model_name_or_path=stable_model_path,
|
29 |
+
controlnet=controlnet,
|
30 |
+
safety_checker=None,
|
31 |
+
torch_dtype=torch.float16,
|
32 |
+
)
|
33 |
+
|
34 |
+
self.pipe = get_scheduler_list(pipe=self.pipe, scheduler=scheduler)
|
35 |
+
self.pipe.to("cuda")
|
36 |
+
self.pipe.enable_xformers_memory_efficient_attention()
|
37 |
+
|
38 |
+
return self.pipe
|
39 |
+
|
40 |
+
def controlnet_hed(self, image_path: str):
|
41 |
+
hed = HEDdetector.from_pretrained("lllyasviel/ControlNet")
|
42 |
+
image = Image.open(image_path)
|
43 |
+
image = hed(image)
|
44 |
+
|
45 |
+
return image
|
46 |
+
|
47 |
+
def generate_image(
|
48 |
+
self,
|
49 |
+
image_path: str,
|
50 |
+
stable_model_path: str,
|
51 |
+
controlnet_hed_model_path: str,
|
52 |
+
prompt: str,
|
53 |
+
negative_prompt: str,
|
54 |
+
num_images_per_prompt: int,
|
55 |
+
guidance_scale: int,
|
56 |
+
num_inference_step: int,
|
57 |
+
sheduler: str,
|
58 |
+
seed_generator: int,
|
59 |
+
):
|
60 |
+
|
61 |
+
image = self.controlnet_hed(image_path=image_path)
|
62 |
+
|
63 |
+
pipe = self.load_model(
|
64 |
+
stable_model_path=stable_model_path,
|
65 |
+
controlnet_model_path=controlnet_hed_model_path,
|
66 |
+
scheduler=sheduler,
|
67 |
+
)
|
68 |
+
|
69 |
+
if seed_generator == 0:
|
70 |
+
random_seed = torch.randint(0, 1000000, (1,))
|
71 |
+
generator = torch.manual_seed(random_seed)
|
72 |
+
else:
|
73 |
+
generator = torch.manual_seed(seed_generator)
|
74 |
+
|
75 |
+
output = pipe(
|
76 |
+
prompt=prompt,
|
77 |
+
image=image,
|
78 |
+
negative_prompt=negative_prompt,
|
79 |
+
num_images_per_prompt=num_images_per_prompt,
|
80 |
+
num_inference_steps=num_inference_step,
|
81 |
+
guidance_scale=guidance_scale,
|
82 |
+
generator=generator,
|
83 |
+
).images
|
84 |
+
|
85 |
+
return output
|
86 |
+
|
87 |
+
def app():
|
88 |
+
with gr.Blocks():
|
89 |
+
with gr.Row():
|
90 |
+
with gr.Column():
|
91 |
+
controlnet_hed_image_file = gr.Image(
|
92 |
+
type="filepath", label="Image"
|
93 |
+
)
|
94 |
+
controlnet_hed_prompt = gr.Textbox(
|
95 |
+
lines=1,
|
96 |
+
show_label=False,
|
97 |
+
placeholder="Prompt",
|
98 |
+
)
|
99 |
+
|
100 |
+
controlnet_hed_negative_prompt = gr.Textbox(
|
101 |
+
lines=1,
|
102 |
+
show_label=False,
|
103 |
+
placeholder="Negative Prompt",
|
104 |
+
)
|
105 |
+
|
106 |
+
with gr.Row():
|
107 |
+
with gr.Column():
|
108 |
+
controlnet_hed_stable_model_id = gr.Dropdown(
|
109 |
+
choices=stable_model_list,
|
110 |
+
value=stable_model_list[0],
|
111 |
+
label="Stable Model Id",
|
112 |
+
)
|
113 |
+
controlnet_hed_guidance_scale = gr.Slider(
|
114 |
+
minimum=0.1,
|
115 |
+
maximum=15,
|
116 |
+
step=0.1,
|
117 |
+
value=7.5,
|
118 |
+
label="Guidance Scale",
|
119 |
+
)
|
120 |
+
controlnet_hed_num_inference_step = gr.Slider(
|
121 |
+
minimum=1,
|
122 |
+
maximum=100,
|
123 |
+
step=1,
|
124 |
+
value=50,
|
125 |
+
label="Num Inference Step",
|
126 |
+
)
|
127 |
+
|
128 |
+
controlnet_hed_num_images_per_prompt = gr.Slider(
|
129 |
+
minimum=1,
|
130 |
+
maximum=10,
|
131 |
+
step=1,
|
132 |
+
value=1,
|
133 |
+
label="Number Of Images",
|
134 |
+
)
|
135 |
+
|
136 |
+
with gr.Row():
|
137 |
+
with gr.Column():
|
138 |
+
controlnet_hed_model_id = gr.Dropdown(
|
139 |
+
choices=controlnet_hed_model_list,
|
140 |
+
value=controlnet_hed_model_list[0],
|
141 |
+
label="ControlNet Model Id",
|
142 |
+
)
|
143 |
+
controlnet_hed_scheduler = gr.Dropdown(
|
144 |
+
choices=SCHEDULER_LIST,
|
145 |
+
value=SCHEDULER_LIST[0],
|
146 |
+
label="Scheduler",
|
147 |
+
)
|
148 |
+
|
149 |
+
controlnet_hed_seed_generator = gr.Number(
|
150 |
+
minimum=0,
|
151 |
+
maximum=1000000,
|
152 |
+
step=1,
|
153 |
+
value=0,
|
154 |
+
label="Seed Generator",
|
155 |
+
)
|
156 |
+
|
157 |
+
controlnet_hed_predict = gr.Button(value="Generator")
|
158 |
+
|
159 |
+
with gr.Column():
|
160 |
+
output_image = gr.Gallery(
|
161 |
+
label="Generated images",
|
162 |
+
show_label=False,
|
163 |
+
elem_id="gallery",
|
164 |
+
).style(grid=(1, 2))
|
165 |
+
|
166 |
+
controlnet_hed_predict.click(
|
167 |
+
fn=StableDiffusionControlNetHEDGenerator().generate_image,
|
168 |
+
inputs=[
|
169 |
+
controlnet_hed_image_file,
|
170 |
+
controlnet_hed_stable_model_id,
|
171 |
+
controlnet_hed_model_id,
|
172 |
+
controlnet_hed_prompt,
|
173 |
+
controlnet_hed_negative_prompt,
|
174 |
+
controlnet_hed_num_images_per_prompt,
|
175 |
+
controlnet_hed_guidance_scale,
|
176 |
+
controlnet_hed_num_inference_step,
|
177 |
+
controlnet_hed_scheduler,
|
178 |
+
controlnet_hed_seed_generator,
|
179 |
+
],
|
180 |
+
outputs=[output_image],
|
181 |
+
)
|
diffusion_webui/diffusion_models/controlnet/controlnet_inpaint/__init__.py
ADDED
File without changes
|
diffusion_webui/diffusion_models/controlnet/controlnet_inpaint/controlnet_inpaint_app.py
ADDED
@@ -0,0 +1,203 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import cv2
|
2 |
+
import gradio as gr
|
3 |
+
import numpy as np
|
4 |
+
import torch
|
5 |
+
from diffusers import (
|
6 |
+
ControlNetModel,
|
7 |
+
StableDiffusionControlNetPipeline,
|
8 |
+
)
|
9 |
+
from PIL import Image
|
10 |
+
|
11 |
+
from diffusion_webui.utils.model_list import (
|
12 |
+
controlnet_canny_model_list,
|
13 |
+
stable_model_list,
|
14 |
+
)
|
15 |
+
from diffusion_webui.utils.scheduler_list import (
|
16 |
+
SCHEDULER_LIST,
|
17 |
+
get_scheduler_list,
|
18 |
+
)
|
19 |
+
|
20 |
+
|
21 |
+
class StableDiffusionControlInpaintNetCannyGenerator:
|
22 |
+
def __init__(self):
|
23 |
+
self.pipe = None
|
24 |
+
|
25 |
+
def controlnet_canny_inpaint(
|
26 |
+
self,
|
27 |
+
image_path: str,
|
28 |
+
):
|
29 |
+
image = Image.open(image_path)
|
30 |
+
image = np.array(image)
|
31 |
+
|
32 |
+
image = cv2.Canny(image, 100, 200)
|
33 |
+
image = image[:, :, None]
|
34 |
+
image = np.concatenate([image, image, image], axis=2)
|
35 |
+
image = Image.fromarray(image)
|
36 |
+
|
37 |
+
return image
|
38 |
+
|
39 |
+
def load_model(self, stable_model_path, controlnet_model_path, scheduler):
|
40 |
+
if self.pipe is None:
|
41 |
+
controlnet = ControlNetModel.from_pretrained(
|
42 |
+
controlnet_model_path, torch_dtype=torch.float16
|
43 |
+
)
|
44 |
+
self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
|
45 |
+
pretrained_model_name_or_path=stable_model_path,
|
46 |
+
controlnet=controlnet,
|
47 |
+
safety_checker=None,
|
48 |
+
torch_dtype=torch.float16,
|
49 |
+
)
|
50 |
+
|
51 |
+
self.pipe = get_scheduler_list(pipe=self.pipe, scheduler=scheduler)
|
52 |
+
self.pipe.to("cuda")
|
53 |
+
self.pipe.enable_xformers_memory_efficient_attention()
|
54 |
+
|
55 |
+
return self.pipe
|
56 |
+
|
57 |
+
def generate_image(
|
58 |
+
self,
|
59 |
+
image_path: str,
|
60 |
+
stable_model_path: str,
|
61 |
+
controlnet_model_path: str,
|
62 |
+
prompt: str,
|
63 |
+
negative_prompt: str,
|
64 |
+
num_images_per_prompt: int,
|
65 |
+
guidance_scale: int,
|
66 |
+
num_inference_step: int,
|
67 |
+
scheduler: str,
|
68 |
+
seed_generator: int,
|
69 |
+
):
|
70 |
+
|
71 |
+
image = self.controlnet_canny_inpaint(
|
72 |
+
image_path=image_path, controlnet_model_path=controlnet_model_path
|
73 |
+
)
|
74 |
+
|
75 |
+
pipe = self.load_model(
|
76 |
+
stable_model_path=stable_model_path,
|
77 |
+
controlnet_model_path=controlnet_model_path,
|
78 |
+
scheduler=scheduler,
|
79 |
+
)
|
80 |
+
|
81 |
+
if seed_generator == 0:
|
82 |
+
random_seed = torch.randint(0, 1000000, (1,))
|
83 |
+
generator = torch.manual_seed(random_seed)
|
84 |
+
else:
|
85 |
+
generator = torch.manual_seed(seed_generator)
|
86 |
+
|
87 |
+
output = pipe(
|
88 |
+
prompt=prompt,
|
89 |
+
image=image,
|
90 |
+
negative_prompt=negative_prompt,
|
91 |
+
num_images_per_prompt=num_images_per_prompt,
|
92 |
+
num_inference_steps=num_inference_step,
|
93 |
+
guidance_scale=guidance_scale,
|
94 |
+
generator=generator,
|
95 |
+
).images
|
96 |
+
|
97 |
+
return output
|
98 |
+
|
99 |
+
def app():
|
100 |
+
with gr.Blocks():
|
101 |
+
with gr.Row():
|
102 |
+
with gr.Column():
|
103 |
+
controlnet_canny_inpaint_image_file = gr.Image(
|
104 |
+
type="filepath", label="Image"
|
105 |
+
)
|
106 |
+
|
107 |
+
controlnet_canny_inpaint_prompt = gr.Textbox(
|
108 |
+
lines=1, placeholder="Prompt", show_label=False
|
109 |
+
)
|
110 |
+
|
111 |
+
controlnet_canny_inpaint_negative_prompt = gr.Textbox(
|
112 |
+
lines=1,
|
113 |
+
show_label=False,
|
114 |
+
placeholder="Negative Prompt",
|
115 |
+
)
|
116 |
+
with gr.Row():
|
117 |
+
with gr.Column():
|
118 |
+
controlnet_canny_inpaint_stable_model_id = (
|
119 |
+
gr.Dropdown(
|
120 |
+
choices=stable_model_list,
|
121 |
+
value=stable_model_list[0],
|
122 |
+
label="Stable Model Id",
|
123 |
+
)
|
124 |
+
)
|
125 |
+
|
126 |
+
controlnet_canny_inpaint_guidance_scale = gr.Slider(
|
127 |
+
minimum=0.1,
|
128 |
+
maximum=15,
|
129 |
+
step=0.1,
|
130 |
+
value=7.5,
|
131 |
+
label="Guidance Scale",
|
132 |
+
)
|
133 |
+
|
134 |
+
controlnet_canny_inpaint_num_inference_step = (
|
135 |
+
gr.Slider(
|
136 |
+
minimum=1,
|
137 |
+
maximum=100,
|
138 |
+
step=1,
|
139 |
+
value=50,
|
140 |
+
label="Num Inference Step",
|
141 |
+
)
|
142 |
+
)
|
143 |
+
controlnet_canny_inpaint_num_images_per_prompt = (
|
144 |
+
gr.Slider(
|
145 |
+
minimum=1,
|
146 |
+
maximum=10,
|
147 |
+
step=1,
|
148 |
+
value=1,
|
149 |
+
label="Number Of Images",
|
150 |
+
)
|
151 |
+
)
|
152 |
+
with gr.Row():
|
153 |
+
with gr.Column():
|
154 |
+
controlnet_canny_inpaint_model_id = gr.Dropdown(
|
155 |
+
choices=controlnet_canny_model_list,
|
156 |
+
value=controlnet_canny_model_list[0],
|
157 |
+
label="Controlnet Model Id",
|
158 |
+
)
|
159 |
+
controlnet_canny_inpaint_scheduler = (
|
160 |
+
gr.Dropdown(
|
161 |
+
choices=SCHEDULER_LIST,
|
162 |
+
value=SCHEDULER_LIST[0],
|
163 |
+
label="Scheduler",
|
164 |
+
)
|
165 |
+
)
|
166 |
+
|
167 |
+
controlnet_canny_inpaint_seed_generator = (
|
168 |
+
gr.Slider(
|
169 |
+
minimum=0,
|
170 |
+
maximum=1000000,
|
171 |
+
step=1,
|
172 |
+
value=0,
|
173 |
+
label="Seed Generator",
|
174 |
+
)
|
175 |
+
)
|
176 |
+
|
177 |
+
controlnet_canny_inpaint_predict = gr.Button(
|
178 |
+
value="Generator"
|
179 |
+
)
|
180 |
+
|
181 |
+
with gr.Column():
|
182 |
+
output_image = gr.Gallery(
|
183 |
+
label="Generated images",
|
184 |
+
show_label=False,
|
185 |
+
elem_id="gallery",
|
186 |
+
).style(grid=(1, 2))
|
187 |
+
|
188 |
+
controlnet_canny_inpaint_predict.click(
|
189 |
+
fn=StableDiffusionControlInpaintNetCannyGenerator().generate_image,
|
190 |
+
inputs=[
|
191 |
+
controlnet_canny_inpaint_image_file,
|
192 |
+
controlnet_canny_inpaint_stable_model_id,
|
193 |
+
controlnet_canny_inpaint_model_id,
|
194 |
+
controlnet_canny_inpaint_prompt,
|
195 |
+
controlnet_canny_inpaint_negative_prompt,
|
196 |
+
controlnet_canny_inpaint_num_images_per_prompt,
|
197 |
+
controlnet_canny_inpaint_guidance_scale,
|
198 |
+
controlnet_canny_inpaint_num_inference_step,
|
199 |
+
controlnet_canny_inpaint_scheduler,
|
200 |
+
controlnet_canny_inpaint_seed_generator,
|
201 |
+
],
|
202 |
+
outputs=[output_image],
|
203 |
+
)
|
diffusion_webui/diffusion_models/controlnet/controlnet_inpaint/pipeline_stable_diffusion_controlnet_inpaint.py
ADDED
@@ -0,0 +1,607 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Copyright 2023 The HuggingFace Team. All rights reserved.
|
2 |
+
#
|
3 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
4 |
+
# you may not use this file except in compliance with the License.
|
5 |
+
# You may obtain a copy of the License at
|
6 |
+
#
|
7 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
8 |
+
#
|
9 |
+
# Unless required by applicable law or agreed to in writing, software
|
10 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
11 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
12 |
+
# See the License for the specific language governing permissions and
|
13 |
+
# limitations under the License.
|
14 |
+
|
15 |
+
import numpy as np
|
16 |
+
import PIL.Image
|
17 |
+
import torch
|
18 |
+
from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_controlnet import *
|
19 |
+
|
20 |
+
EXAMPLE_DOC_STRING = """
|
21 |
+
Examples:
|
22 |
+
```py
|
23 |
+
>>> # !pip install opencv-python transformers accelerate
|
24 |
+
>>> from diffusers import StableDiffusionControlNetInpaintPipeline, ControlNetModel, UniPCMultistepScheduler
|
25 |
+
>>> from diffusers.utils import load_image
|
26 |
+
>>> import numpy as np
|
27 |
+
>>> import torch
|
28 |
+
|
29 |
+
>>> import cv2
|
30 |
+
>>> from PIL import Image
|
31 |
+
>>> # download an image
|
32 |
+
>>> image = load_image(
|
33 |
+
... "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png"
|
34 |
+
... )
|
35 |
+
>>> image = np.array(image)
|
36 |
+
>>> mask_image = load_image(
|
37 |
+
... "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png"
|
38 |
+
... )
|
39 |
+
>>> mask_image = np.array(mask_image)
|
40 |
+
>>> # get canny image
|
41 |
+
>>> canny_image = cv2.Canny(image, 100, 200)
|
42 |
+
>>> canny_image = canny_image[:, :, None]
|
43 |
+
>>> canny_image = np.concatenate([canny_image, canny_image, canny_image], axis=2)
|
44 |
+
>>> canny_image = Image.fromarray(canny_image)
|
45 |
+
|
46 |
+
>>> # load control net and stable diffusion v1-5
|
47 |
+
>>> controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)
|
48 |
+
>>> pipe = StableDiffusionControlNetInpaintPipeline.from_pretrained(
|
49 |
+
... "runwayml/stable-diffusion-inpainting", controlnet=controlnet, torch_dtype=torch.float16
|
50 |
+
... )
|
51 |
+
|
52 |
+
>>> # speed up diffusion process with faster scheduler and memory optimization
|
53 |
+
>>> pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
|
54 |
+
>>> # remove following line if xformers is not installed
|
55 |
+
>>> pipe.enable_xformers_memory_efficient_attention()
|
56 |
+
|
57 |
+
>>> pipe.enable_model_cpu_offload()
|
58 |
+
|
59 |
+
>>> # generate image
|
60 |
+
>>> generator = torch.manual_seed(0)
|
61 |
+
>>> image = pipe(
|
62 |
+
... "futuristic-looking doggo",
|
63 |
+
... num_inference_steps=20,
|
64 |
+
... generator=generator,
|
65 |
+
... image=image,
|
66 |
+
... control_image=canny_image,
|
67 |
+
... mask_image=mask_image
|
68 |
+
... ).images[0]
|
69 |
+
```
|
70 |
+
"""
|
71 |
+
|
72 |
+
|
73 |
+
def prepare_mask_and_masked_image(image, mask):
|
74 |
+
"""
|
75 |
+
Prepares a pair (image, mask) to be consumed by the Stable Diffusion pipeline. This means that those inputs will be
|
76 |
+
converted to ``torch.Tensor`` with shapes ``batch x channels x height x width`` where ``channels`` is ``3`` for the
|
77 |
+
``image`` and ``1`` for the ``mask``.
|
78 |
+
The ``image`` will be converted to ``torch.float32`` and normalized to be in ``[-1, 1]``. The ``mask`` will be
|
79 |
+
binarized (``mask > 0.5``) and cast to ``torch.float32`` too.
|
80 |
+
Args:
|
81 |
+
image (Union[np.array, PIL.Image, torch.Tensor]): The image to inpaint.
|
82 |
+
It can be a ``PIL.Image``, or a ``height x width x 3`` ``np.array`` or a ``channels x height x width``
|
83 |
+
``torch.Tensor`` or a ``batch x channels x height x width`` ``torch.Tensor``.
|
84 |
+
mask (_type_): The mask to apply to the image, i.e. regions to inpaint.
|
85 |
+
It can be a ``PIL.Image``, or a ``height x width`` ``np.array`` or a ``1 x height x width``
|
86 |
+
``torch.Tensor`` or a ``batch x 1 x height x width`` ``torch.Tensor``.
|
87 |
+
Raises:
|
88 |
+
ValueError: ``torch.Tensor`` images should be in the ``[-1, 1]`` range. ValueError: ``torch.Tensor`` mask
|
89 |
+
should be in the ``[0, 1]`` range. ValueError: ``mask`` and ``image`` should have the same spatial dimensions.
|
90 |
+
TypeError: ``mask`` is a ``torch.Tensor`` but ``image`` is not
|
91 |
+
(ot the other way around).
|
92 |
+
Returns:
|
93 |
+
tuple[torch.Tensor]: The pair (mask, masked_image) as ``torch.Tensor`` with 4
|
94 |
+
dimensions: ``batch x channels x height x width``.
|
95 |
+
"""
|
96 |
+
if isinstance(image, torch.Tensor):
|
97 |
+
if not isinstance(mask, torch.Tensor):
|
98 |
+
raise TypeError(
|
99 |
+
f"`image` is a torch.Tensor but `mask` (type: {type(mask)} is not"
|
100 |
+
)
|
101 |
+
|
102 |
+
# Batch single image
|
103 |
+
if image.ndim == 3:
|
104 |
+
assert (
|
105 |
+
image.shape[0] == 3
|
106 |
+
), "Image outside a batch should be of shape (3, H, W)"
|
107 |
+
image = image.unsqueeze(0)
|
108 |
+
|
109 |
+
# Batch and add channel dim for single mask
|
110 |
+
if mask.ndim == 2:
|
111 |
+
mask = mask.unsqueeze(0).unsqueeze(0)
|
112 |
+
|
113 |
+
# Batch single mask or add channel dim
|
114 |
+
if mask.ndim == 3:
|
115 |
+
# Single batched mask, no channel dim or single mask not batched but channel dim
|
116 |
+
if mask.shape[0] == 1:
|
117 |
+
mask = mask.unsqueeze(0)
|
118 |
+
|
119 |
+
# Batched masks no channel dim
|
120 |
+
else:
|
121 |
+
mask = mask.unsqueeze(1)
|
122 |
+
|
123 |
+
assert (
|
124 |
+
image.ndim == 4 and mask.ndim == 4
|
125 |
+
), "Image and Mask must have 4 dimensions"
|
126 |
+
assert (
|
127 |
+
image.shape[-2:] == mask.shape[-2:]
|
128 |
+
), "Image and Mask must have the same spatial dimensions"
|
129 |
+
assert (
|
130 |
+
image.shape[0] == mask.shape[0]
|
131 |
+
), "Image and Mask must have the same batch size"
|
132 |
+
|
133 |
+
# Check image is in [-1, 1]
|
134 |
+
if image.min() < -1 or image.max() > 1:
|
135 |
+
raise ValueError("Image should be in [-1, 1] range")
|
136 |
+
|
137 |
+
# Check mask is in [0, 1]
|
138 |
+
if mask.min() < 0 or mask.max() > 1:
|
139 |
+
raise ValueError("Mask should be in [0, 1] range")
|
140 |
+
|
141 |
+
# Binarize mask
|
142 |
+
mask[mask < 0.5] = 0
|
143 |
+
mask[mask >= 0.5] = 1
|
144 |
+
|
145 |
+
# Image as float32
|
146 |
+
image = image.to(dtype=torch.float32)
|
147 |
+
elif isinstance(mask, torch.Tensor):
|
148 |
+
raise TypeError(
|
149 |
+
f"`mask` is a torch.Tensor but `image` (type: {type(image)} is not"
|
150 |
+
)
|
151 |
+
else:
|
152 |
+
# preprocess image
|
153 |
+
if isinstance(image, (PIL.Image.Image, np.ndarray)):
|
154 |
+
image = [image]
|
155 |
+
|
156 |
+
if isinstance(image, list) and isinstance(image[0], PIL.Image.Image):
|
157 |
+
image = [np.array(i.convert("RGB"))[None, :] for i in image]
|
158 |
+
image = np.concatenate(image, axis=0)
|
159 |
+
elif isinstance(image, list) and isinstance(image[0], np.ndarray):
|
160 |
+
image = np.concatenate([i[None, :] for i in image], axis=0)
|
161 |
+
|
162 |
+
image = image.transpose(0, 3, 1, 2)
|
163 |
+
image = torch.from_numpy(image).to(dtype=torch.float32) / 127.5 - 1.0
|
164 |
+
|
165 |
+
# preprocess mask
|
166 |
+
if isinstance(mask, (PIL.Image.Image, np.ndarray)):
|
167 |
+
mask = [mask]
|
168 |
+
|
169 |
+
if isinstance(mask, list) and isinstance(mask[0], PIL.Image.Image):
|
170 |
+
mask = np.concatenate(
|
171 |
+
[np.array(m.convert("L"))[None, None, :] for m in mask], axis=0
|
172 |
+
)
|
173 |
+
mask = mask.astype(np.float32) / 255.0
|
174 |
+
elif isinstance(mask, list) and isinstance(mask[0], np.ndarray):
|
175 |
+
mask = np.concatenate([m[None, None, :] for m in mask], axis=0)
|
176 |
+
|
177 |
+
mask[mask < 0.5] = 0
|
178 |
+
mask[mask >= 0.5] = 1
|
179 |
+
mask = torch.from_numpy(mask)
|
180 |
+
|
181 |
+
masked_image = image * (mask < 0.5)
|
182 |
+
|
183 |
+
return mask, masked_image
|
184 |
+
|
185 |
+
|
186 |
+
class StableDiffusionControlNetInpaintPipeline(
|
187 |
+
StableDiffusionControlNetPipeline
|
188 |
+
):
|
189 |
+
r"""
|
190 |
+
Pipeline for text-guided image inpainting using Stable Diffusion with ControlNet guidance.
|
191 |
+
|
192 |
+
This model inherits from [`StableDiffusionControlNetPipeline`]. Check the superclass documentation for the generic methods the
|
193 |
+
library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.)
|
194 |
+
|
195 |
+
Args:
|
196 |
+
vae ([`AutoencoderKL`]):
|
197 |
+
Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.
|
198 |
+
text_encoder ([`CLIPTextModel`]):
|
199 |
+
Frozen text-encoder. Stable Diffusion uses the text portion of
|
200 |
+
[CLIP](https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPTextModel), specifically
|
201 |
+
the [clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) variant.
|
202 |
+
tokenizer (`CLIPTokenizer`):
|
203 |
+
Tokenizer of class
|
204 |
+
[CLIPTokenizer](https://huggingface.co/docs/transformers/v4.21.0/en/model_doc/clip#transformers.CLIPTokenizer).
|
205 |
+
unet ([`UNet2DConditionModel`]): Conditional U-Net architecture to denoise the encoded image latents.
|
206 |
+
controlnet ([`ControlNetModel`]):
|
207 |
+
Provides additional conditioning to the unet during the denoising process
|
208 |
+
scheduler ([`SchedulerMixin`]):
|
209 |
+
A scheduler to be used in combination with `unet` to denoise the encoded image latents. Can be one of
|
210 |
+
[`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
|
211 |
+
safety_checker ([`StableDiffusionSafetyChecker`]):
|
212 |
+
Classification module that estimates whether generated images could be considered offensive or harmful.
|
213 |
+
Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
|
214 |
+
feature_extractor ([`CLIPFeatureExtractor`]):
|
215 |
+
Model that extracts features from generated images to be used as inputs for the `safety_checker`.
|
216 |
+
"""
|
217 |
+
|
218 |
+
def prepare_mask_latents(
|
219 |
+
self,
|
220 |
+
mask,
|
221 |
+
masked_image,
|
222 |
+
batch_size,
|
223 |
+
height,
|
224 |
+
width,
|
225 |
+
dtype,
|
226 |
+
device,
|
227 |
+
generator,
|
228 |
+
do_classifier_free_guidance,
|
229 |
+
):
|
230 |
+
# resize the mask to latents shape as we concatenate the mask to the latents
|
231 |
+
# we do that before converting to dtype to avoid breaking in case we're using cpu_offload
|
232 |
+
# and half precision
|
233 |
+
mask = torch.nn.functional.interpolate(
|
234 |
+
mask,
|
235 |
+
size=(
|
236 |
+
height // self.vae_scale_factor,
|
237 |
+
width // self.vae_scale_factor,
|
238 |
+
),
|
239 |
+
)
|
240 |
+
mask = mask.to(device=device, dtype=dtype)
|
241 |
+
|
242 |
+
masked_image = masked_image.to(device=device, dtype=dtype)
|
243 |
+
|
244 |
+
# encode the mask image into latents space so we can concatenate it to the latents
|
245 |
+
if isinstance(generator, list):
|
246 |
+
masked_image_latents = [
|
247 |
+
self.vae.encode(masked_image[i : i + 1]).latent_dist.sample(
|
248 |
+
generator=generator[i]
|
249 |
+
)
|
250 |
+
for i in range(batch_size)
|
251 |
+
]
|
252 |
+
masked_image_latents = torch.cat(masked_image_latents, dim=0)
|
253 |
+
else:
|
254 |
+
masked_image_latents = self.vae.encode(
|
255 |
+
masked_image
|
256 |
+
).latent_dist.sample(generator=generator)
|
257 |
+
masked_image_latents = (
|
258 |
+
self.vae.config.scaling_factor * masked_image_latents
|
259 |
+
)
|
260 |
+
|
261 |
+
# duplicate mask and masked_image_latents for each generation per prompt, using mps friendly method
|
262 |
+
if mask.shape[0] < batch_size:
|
263 |
+
if not batch_size % mask.shape[0] == 0:
|
264 |
+
raise ValueError(
|
265 |
+
"The passed mask and the required batch size don't match. Masks are supposed to be duplicated to"
|
266 |
+
f" a total batch size of {batch_size}, but {mask.shape[0]} masks were passed. Make sure the number"
|
267 |
+
" of masks that you pass is divisible by the total requested batch size."
|
268 |
+
)
|
269 |
+
mask = mask.repeat(batch_size // mask.shape[0], 1, 1, 1)
|
270 |
+
if masked_image_latents.shape[0] < batch_size:
|
271 |
+
if not batch_size % masked_image_latents.shape[0] == 0:
|
272 |
+
raise ValueError(
|
273 |
+
"The passed images and the required batch size don't match. Images are supposed to be duplicated"
|
274 |
+
f" to a total batch size of {batch_size}, but {masked_image_latents.shape[0]} images were passed."
|
275 |
+
" Make sure the number of images that you pass is divisible by the total requested batch size."
|
276 |
+
)
|
277 |
+
masked_image_latents = masked_image_latents.repeat(
|
278 |
+
batch_size // masked_image_latents.shape[0], 1, 1, 1
|
279 |
+
)
|
280 |
+
|
281 |
+
mask = torch.cat([mask] * 2) if do_classifier_free_guidance else mask
|
282 |
+
masked_image_latents = (
|
283 |
+
torch.cat([masked_image_latents] * 2)
|
284 |
+
if do_classifier_free_guidance
|
285 |
+
else masked_image_latents
|
286 |
+
)
|
287 |
+
|
288 |
+
# aligning device to prevent device errors when concating it with the latent model input
|
289 |
+
masked_image_latents = masked_image_latents.to(
|
290 |
+
device=device, dtype=dtype
|
291 |
+
)
|
292 |
+
return mask, masked_image_latents
|
293 |
+
|
294 |
+
@torch.no_grad()
|
295 |
+
@replace_example_docstring(EXAMPLE_DOC_STRING)
|
296 |
+
def __call__(
|
297 |
+
self,
|
298 |
+
prompt: Union[str, List[str]] = None,
|
299 |
+
image: Union[torch.FloatTensor, PIL.Image.Image] = None,
|
300 |
+
control_image: Union[
|
301 |
+
torch.FloatTensor,
|
302 |
+
PIL.Image.Image,
|
303 |
+
List[torch.FloatTensor],
|
304 |
+
List[PIL.Image.Image],
|
305 |
+
] = None,
|
306 |
+
mask_image: Union[torch.FloatTensor, PIL.Image.Image] = None,
|
307 |
+
height: Optional[int] = None,
|
308 |
+
width: Optional[int] = None,
|
309 |
+
num_inference_steps: int = 50,
|
310 |
+
guidance_scale: float = 7.5,
|
311 |
+
negative_prompt: Optional[Union[str, List[str]]] = None,
|
312 |
+
num_images_per_prompt: Optional[int] = 1,
|
313 |
+
eta: float = 0.0,
|
314 |
+
generator: Optional[
|
315 |
+
Union[torch.Generator, List[torch.Generator]]
|
316 |
+
] = None,
|
317 |
+
latents: Optional[torch.FloatTensor] = None,
|
318 |
+
prompt_embeds: Optional[torch.FloatTensor] = None,
|
319 |
+
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
|
320 |
+
output_type: Optional[str] = "pil",
|
321 |
+
return_dict: bool = True,
|
322 |
+
callback: Optional[
|
323 |
+
Callable[[int, int, torch.FloatTensor], None]
|
324 |
+
] = None,
|
325 |
+
callback_steps: int = 1,
|
326 |
+
cross_attention_kwargs: Optional[Dict[str, Any]] = None,
|
327 |
+
controlnet_conditioning_scale: float = 1.0,
|
328 |
+
):
|
329 |
+
r"""
|
330 |
+
Function invoked when calling the pipeline for generation.
|
331 |
+
Args:
|
332 |
+
prompt (`str` or `List[str]`, *optional*):
|
333 |
+
The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
|
334 |
+
instead.
|
335 |
+
image (`PIL.Image.Image`):
|
336 |
+
`Image`, or tensor representing an image batch which will be inpainted, *i.e.* parts of the image will
|
337 |
+
be masked out with `mask_image` and repainted according to `prompt`.
|
338 |
+
control_image (`torch.FloatTensor`, `PIL.Image.Image`, `List[torch.FloatTensor]` or `List[PIL.Image.Image]`):
|
339 |
+
The ControlNet input condition. ControlNet uses this input condition to generate guidance to Unet. If
|
340 |
+
the type is specified as `Torch.FloatTensor`, it is passed to ControlNet as is. PIL.Image.Image` can
|
341 |
+
also be accepted as an image. The control image is automatically resized to fit the output image.
|
342 |
+
mask_image (`PIL.Image.Image`):
|
343 |
+
`Image`, or tensor representing an image batch, to mask `image`. White pixels in the mask will be
|
344 |
+
repainted, while black pixels will be preserved. If `mask_image` is a PIL image, it will be converted
|
345 |
+
to a single channel (luminance) before use. If it's a tensor, it should contain one color channel (L)
|
346 |
+
instead of 3, so the expected shape would be `(B, H, W, 1)`.
|
347 |
+
height (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
|
348 |
+
The height in pixels of the generated image.
|
349 |
+
width (`int`, *optional*, defaults to self.unet.config.sample_size * self.vae_scale_factor):
|
350 |
+
The width in pixels of the generated image.
|
351 |
+
num_inference_steps (`int`, *optional*, defaults to 50):
|
352 |
+
The number of denoising steps. More denoising steps usually lead to a higher quality image at the
|
353 |
+
expense of slower inference.
|
354 |
+
guidance_scale (`float`, *optional*, defaults to 7.5):
|
355 |
+
Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
|
356 |
+
`guidance_scale` is defined as `w` of equation 2. of [Imagen
|
357 |
+
Paper](https://arxiv.org/pdf/2205.11487.pdf). Guidance scale is enabled by setting `guidance_scale >
|
358 |
+
1`. Higher guidance scale encourages to generate images that are closely linked to the text `prompt`,
|
359 |
+
usually at the expense of lower image quality.
|
360 |
+
negative_prompt (`str` or `List[str]`, *optional*):
|
361 |
+
The prompt or prompts not to guide the image generation. If not defined, one has to pass
|
362 |
+
`negative_prompt_embeds`. instead. If not defined, one has to pass `negative_prompt_embeds`. instead.
|
363 |
+
Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`).
|
364 |
+
num_images_per_prompt (`int`, *optional*, defaults to 1):
|
365 |
+
The number of images to generate per prompt.
|
366 |
+
eta (`float`, *optional*, defaults to 0.0):
|
367 |
+
Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to
|
368 |
+
[`schedulers.DDIMScheduler`], will be ignored for others.
|
369 |
+
generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
|
370 |
+
One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
|
371 |
+
to make generation deterministic.
|
372 |
+
latents (`torch.FloatTensor`, *optional*):
|
373 |
+
Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
|
374 |
+
generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
|
375 |
+
tensor will ge generated by sampling using the supplied random `generator`.
|
376 |
+
prompt_embeds (`torch.FloatTensor`, *optional*):
|
377 |
+
Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
|
378 |
+
provided, text embeddings will be generated from `prompt` input argument.
|
379 |
+
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
|
380 |
+
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
|
381 |
+
weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
|
382 |
+
argument.
|
383 |
+
output_type (`str`, *optional*, defaults to `"pil"`):
|
384 |
+
The output format of the generate image. Choose between
|
385 |
+
[PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.Image` or `np.array`.
|
386 |
+
return_dict (`bool`, *optional*, defaults to `True`):
|
387 |
+
Whether or not to return a [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] instead of a
|
388 |
+
plain tuple.
|
389 |
+
callback (`Callable`, *optional*):
|
390 |
+
A function that will be called every `callback_steps` steps during inference. The function will be
|
391 |
+
called with the following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
|
392 |
+
callback_steps (`int`, *optional*, defaults to 1):
|
393 |
+
The frequency at which the `callback` function will be called. If not specified, the callback will be
|
394 |
+
called at every step.
|
395 |
+
cross_attention_kwargs (`dict`, *optional*):
|
396 |
+
A kwargs dictionary that if specified is passed along to the `AttnProcessor` as defined under
|
397 |
+
`self.processor` in
|
398 |
+
[diffusers.cross_attention](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/cross_attention.py).
|
399 |
+
controlnet_conditioning_scale (`float`, *optional*, defaults to 1.0):
|
400 |
+
The outputs of the controlnet are multiplied by `controlnet_conditioning_scale` before they are added
|
401 |
+
to the residual in the original unet.
|
402 |
+
Examples:
|
403 |
+
Returns:
|
404 |
+
[`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] or `tuple`:
|
405 |
+
[`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] if `return_dict` is True, otherwise a `tuple.
|
406 |
+
When returning a tuple, the first element is a list with the generated images, and the second element is a
|
407 |
+
list of `bool`s denoting whether the corresponding generated image likely represents "not-safe-for-work"
|
408 |
+
(nsfw) content, according to the `safety_checker`.
|
409 |
+
"""
|
410 |
+
# 0. Default height and width to unet
|
411 |
+
height, width = self._default_height_width(height, width, control_image)
|
412 |
+
|
413 |
+
# 1. Check inputs. Raise error if not correct
|
414 |
+
self.check_inputs(
|
415 |
+
prompt,
|
416 |
+
control_image,
|
417 |
+
height,
|
418 |
+
width,
|
419 |
+
callback_steps,
|
420 |
+
negative_prompt,
|
421 |
+
prompt_embeds,
|
422 |
+
negative_prompt_embeds,
|
423 |
+
)
|
424 |
+
|
425 |
+
# 2. Define call parameters
|
426 |
+
if prompt is not None and isinstance(prompt, str):
|
427 |
+
batch_size = 1
|
428 |
+
elif prompt is not None and isinstance(prompt, list):
|
429 |
+
batch_size = len(prompt)
|
430 |
+
else:
|
431 |
+
batch_size = prompt_embeds.shape[0]
|
432 |
+
|
433 |
+
device = self._execution_device
|
434 |
+
# here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
|
435 |
+
# of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
|
436 |
+
# corresponds to doing no classifier free guidance.
|
437 |
+
do_classifier_free_guidance = guidance_scale > 1.0
|
438 |
+
|
439 |
+
# 3. Encode input prompt
|
440 |
+
prompt_embeds = self._encode_prompt(
|
441 |
+
prompt,
|
442 |
+
device,
|
443 |
+
num_images_per_prompt,
|
444 |
+
do_classifier_free_guidance,
|
445 |
+
negative_prompt,
|
446 |
+
prompt_embeds=prompt_embeds,
|
447 |
+
negative_prompt_embeds=negative_prompt_embeds,
|
448 |
+
)
|
449 |
+
|
450 |
+
# 4. Prepare image
|
451 |
+
control_image = self.prepare_image(
|
452 |
+
control_image,
|
453 |
+
width,
|
454 |
+
height,
|
455 |
+
batch_size * num_images_per_prompt,
|
456 |
+
num_images_per_prompt,
|
457 |
+
device,
|
458 |
+
self.controlnet.dtype,
|
459 |
+
)
|
460 |
+
|
461 |
+
if do_classifier_free_guidance:
|
462 |
+
control_image = torch.cat([control_image] * 2)
|
463 |
+
|
464 |
+
# 5. Prepare timesteps
|
465 |
+
self.scheduler.set_timesteps(num_inference_steps, device=device)
|
466 |
+
timesteps = self.scheduler.timesteps
|
467 |
+
|
468 |
+
# 6. Prepare latent variables
|
469 |
+
num_channels_latents = self.controlnet.in_channels
|
470 |
+
latents = self.prepare_latents(
|
471 |
+
batch_size * num_images_per_prompt,
|
472 |
+
num_channels_latents,
|
473 |
+
height,
|
474 |
+
width,
|
475 |
+
prompt_embeds.dtype,
|
476 |
+
device,
|
477 |
+
generator,
|
478 |
+
latents,
|
479 |
+
)
|
480 |
+
|
481 |
+
# EXTRA: prepare mask latents
|
482 |
+
mask, masked_image = prepare_mask_and_masked_image(image, mask_image)
|
483 |
+
mask, masked_image_latents = self.prepare_mask_latents(
|
484 |
+
mask,
|
485 |
+
masked_image,
|
486 |
+
batch_size * num_images_per_prompt,
|
487 |
+
height,
|
488 |
+
width,
|
489 |
+
prompt_embeds.dtype,
|
490 |
+
device,
|
491 |
+
generator,
|
492 |
+
do_classifier_free_guidance,
|
493 |
+
)
|
494 |
+
|
495 |
+
# 7. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline
|
496 |
+
extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)
|
497 |
+
|
498 |
+
# 8. Denoising loop
|
499 |
+
num_warmup_steps = (
|
500 |
+
len(timesteps) - num_inference_steps * self.scheduler.order
|
501 |
+
)
|
502 |
+
with self.progress_bar(total=num_inference_steps) as progress_bar:
|
503 |
+
for i, t in enumerate(timesteps):
|
504 |
+
# expand the latents if we are doing classifier free guidance
|
505 |
+
latent_model_input = (
|
506 |
+
torch.cat([latents] * 2)
|
507 |
+
if do_classifier_free_guidance
|
508 |
+
else latents
|
509 |
+
)
|
510 |
+
latent_model_input = self.scheduler.scale_model_input(
|
511 |
+
latent_model_input, t
|
512 |
+
)
|
513 |
+
|
514 |
+
down_block_res_samples, mid_block_res_sample = self.controlnet(
|
515 |
+
latent_model_input,
|
516 |
+
t,
|
517 |
+
encoder_hidden_states=prompt_embeds,
|
518 |
+
controlnet_cond=control_image,
|
519 |
+
return_dict=False,
|
520 |
+
)
|
521 |
+
|
522 |
+
down_block_res_samples = [
|
523 |
+
down_block_res_sample * controlnet_conditioning_scale
|
524 |
+
for down_block_res_sample in down_block_res_samples
|
525 |
+
]
|
526 |
+
mid_block_res_sample *= controlnet_conditioning_scale
|
527 |
+
|
528 |
+
# predict the noise residual
|
529 |
+
latent_model_input = torch.cat(
|
530 |
+
[latent_model_input, mask, masked_image_latents], dim=1
|
531 |
+
)
|
532 |
+
noise_pred = self.unet(
|
533 |
+
latent_model_input,
|
534 |
+
t,
|
535 |
+
encoder_hidden_states=prompt_embeds,
|
536 |
+
cross_attention_kwargs=cross_attention_kwargs,
|
537 |
+
down_block_additional_residuals=down_block_res_samples,
|
538 |
+
mid_block_additional_residual=mid_block_res_sample,
|
539 |
+
).sample
|
540 |
+
|
541 |
+
# perform guidance
|
542 |
+
if do_classifier_free_guidance:
|
543 |
+
noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
|
544 |
+
noise_pred = noise_pred_uncond + guidance_scale * (
|
545 |
+
noise_pred_text - noise_pred_uncond
|
546 |
+
)
|
547 |
+
|
548 |
+
# compute the previous noisy sample x_t -> x_t-1
|
549 |
+
latents = self.scheduler.step(
|
550 |
+
noise_pred, t, latents, **extra_step_kwargs
|
551 |
+
).prev_sample
|
552 |
+
|
553 |
+
# call the callback, if provided
|
554 |
+
if i == len(timesteps) - 1 or (
|
555 |
+
(i + 1) > num_warmup_steps
|
556 |
+
and (i + 1) % self.scheduler.order == 0
|
557 |
+
):
|
558 |
+
progress_bar.update()
|
559 |
+
if callback is not None and i % callback_steps == 0:
|
560 |
+
callback(i, t, latents)
|
561 |
+
|
562 |
+
# If we do sequential model offloading, let's offload unet and controlnet
|
563 |
+
# manually for max memory savings
|
564 |
+
if (
|
565 |
+
hasattr(self, "final_offload_hook")
|
566 |
+
and self.final_offload_hook is not None
|
567 |
+
):
|
568 |
+
self.unet.to("cpu")
|
569 |
+
self.controlnet.to("cpu")
|
570 |
+
torch.cuda.empty_cache()
|
571 |
+
|
572 |
+
if output_type == "latent":
|
573 |
+
image = latents
|
574 |
+
has_nsfw_concept = None
|
575 |
+
elif output_type == "pil":
|
576 |
+
# 8. Post-processing
|
577 |
+
image = self.decode_latents(latents)
|
578 |
+
|
579 |
+
# 9. Run safety checker
|
580 |
+
image, has_nsfw_concept = self.run_safety_checker(
|
581 |
+
image, device, prompt_embeds.dtype
|
582 |
+
)
|
583 |
+
|
584 |
+
# 10. Convert to PIL
|
585 |
+
image = self.numpy_to_pil(image)
|
586 |
+
else:
|
587 |
+
# 8. Post-processing
|
588 |
+
image = self.decode_latents(latents)
|
589 |
+
|
590 |
+
# 9. Run safety checker
|
591 |
+
image, has_nsfw_concept = self.run_safety_checker(
|
592 |
+
image, device, prompt_embeds.dtype
|
593 |
+
)
|
594 |
+
|
595 |
+
# Offload last model to CPU
|
596 |
+
if (
|
597 |
+
hasattr(self, "final_offload_hook")
|
598 |
+
and self.final_offload_hook is not None
|
599 |
+
):
|
600 |
+
self.final_offload_hook.offload()
|
601 |
+
|
602 |
+
if not return_dict:
|
603 |
+
return (image, has_nsfw_concept)
|
604 |
+
|
605 |
+
return StableDiffusionPipelineOutput(
|
606 |
+
images=image, nsfw_content_detected=has_nsfw_concept
|
607 |
+
)
|
diffusion_webui/diffusion_models/controlnet/controlnet_mlsd.py
ADDED
@@ -0,0 +1,173 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
import torch
|
3 |
+
from controlnet_aux import MLSDdetector
|
4 |
+
from diffusers import ControlNetModel, StableDiffusionControlNetPipeline
|
5 |
+
from PIL import Image
|
6 |
+
|
7 |
+
from diffusion_webui.utils.model_list import stable_model_list
|
8 |
+
from diffusion_webui.utils.scheduler_list import (
|
9 |
+
SCHEDULER_LIST,
|
10 |
+
get_scheduler_list,
|
11 |
+
)
|
12 |
+
|
13 |
+
|
14 |
+
class StableDiffusionControlNetMLSDGenerator:
|
15 |
+
def __init__(self):
|
16 |
+
self.pipe = None
|
17 |
+
|
18 |
+
def load_model(self, stable_model_path, controlnet_model_path, scheduler):
|
19 |
+
if self.pipe is None:
|
20 |
+
controlnet = ControlNetModel.from_pretrained(
|
21 |
+
controlnet_model_path, torch_dtype=torch.float16
|
22 |
+
)
|
23 |
+
|
24 |
+
self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
|
25 |
+
pretrained_model_name_or_path=stable_model_path,
|
26 |
+
controlnet=controlnet,
|
27 |
+
safety_checker=None,
|
28 |
+
torch_dtype=torch.float16,
|
29 |
+
)
|
30 |
+
|
31 |
+
self.pipe = get_scheduler_list(pipe=self.pipe, scheduler=scheduler)
|
32 |
+
self.pipe.to("cuda")
|
33 |
+
self.pipe.enable_xformers_memory_efficient_attention()
|
34 |
+
|
35 |
+
return self.pipe
|
36 |
+
|
37 |
+
def controlnet_mlsd(self, image_path: str):
|
38 |
+
mlsd = MLSDdetector.from_pretrained("lllyasviel/ControlNet")
|
39 |
+
|
40 |
+
image = Image.open(image_path)
|
41 |
+
image = mlsd(image)
|
42 |
+
|
43 |
+
return image
|
44 |
+
|
45 |
+
def generate_image(
|
46 |
+
self,
|
47 |
+
image_path: str,
|
48 |
+
model_path: str,
|
49 |
+
prompt: str,
|
50 |
+
negative_prompt: str,
|
51 |
+
num_images_per_prompt: int,
|
52 |
+
guidance_scale: int,
|
53 |
+
num_inference_step: int,
|
54 |
+
scheduler: str,
|
55 |
+
seed_generator: int,
|
56 |
+
):
|
57 |
+
image = self.controlnet_mlsd(image_path=image_path)
|
58 |
+
|
59 |
+
pipe = self.load_model(
|
60 |
+
stable_model_path=model_path,
|
61 |
+
controlnet_model_path="lllyasviel/sd-controlnet-mlsd",
|
62 |
+
scheduler=scheduler,
|
63 |
+
)
|
64 |
+
|
65 |
+
if seed_generator == 0:
|
66 |
+
random_seed = torch.randint(0, 1000000, (1,))
|
67 |
+
generator = torch.manual_seed(random_seed)
|
68 |
+
else:
|
69 |
+
generator = torch.manual_seed(seed_generator)
|
70 |
+
|
71 |
+
output = pipe(
|
72 |
+
prompt=prompt,
|
73 |
+
image=image,
|
74 |
+
negative_prompt=negative_prompt,
|
75 |
+
num_images_per_prompt=num_images_per_prompt,
|
76 |
+
num_inference_steps=num_inference_step,
|
77 |
+
guidance_scale=guidance_scale,
|
78 |
+
generator=generator,
|
79 |
+
).images
|
80 |
+
|
81 |
+
return output
|
82 |
+
|
83 |
+
def app():
|
84 |
+
with gr.Blocks():
|
85 |
+
with gr.Row():
|
86 |
+
with gr.Column():
|
87 |
+
controlnet_mlsd_image_file = gr.Image(
|
88 |
+
type="filepath", label="Image"
|
89 |
+
)
|
90 |
+
|
91 |
+
controlnet_mlsd_prompt = gr.Textbox(
|
92 |
+
lines=1,
|
93 |
+
show_label=False,
|
94 |
+
placeholder="Prompt",
|
95 |
+
)
|
96 |
+
|
97 |
+
controlnet_mlsd_negative_prompt = gr.Textbox(
|
98 |
+
lines=1,
|
99 |
+
show_label=False,
|
100 |
+
placeholder="Negative Prompt",
|
101 |
+
)
|
102 |
+
|
103 |
+
with gr.Row():
|
104 |
+
with gr.Column():
|
105 |
+
controlnet_mlsd_model_id = gr.Dropdown(
|
106 |
+
choices=stable_model_list,
|
107 |
+
value=stable_model_list[0],
|
108 |
+
label="Stable Model Id",
|
109 |
+
)
|
110 |
+
controlnet_mlsd_guidance_scale = gr.Slider(
|
111 |
+
minimum=0.1,
|
112 |
+
maximum=15,
|
113 |
+
step=0.1,
|
114 |
+
value=7.5,
|
115 |
+
label="Guidance Scale",
|
116 |
+
)
|
117 |
+
controlnet_mlsd_num_inference_step = gr.Slider(
|
118 |
+
minimum=1,
|
119 |
+
maximum=100,
|
120 |
+
step=1,
|
121 |
+
value=50,
|
122 |
+
label="Num Inference Step",
|
123 |
+
)
|
124 |
+
|
125 |
+
with gr.Row():
|
126 |
+
with gr.Column():
|
127 |
+
controlnet_mlsd_scheduler = gr.Dropdown(
|
128 |
+
choices=SCHEDULER_LIST,
|
129 |
+
value=SCHEDULER_LIST[0],
|
130 |
+
label="Scheduler",
|
131 |
+
)
|
132 |
+
|
133 |
+
controlnet_mlsd_seed_generator = gr.Slider(
|
134 |
+
minimum=0,
|
135 |
+
maximum=1000000,
|
136 |
+
step=1,
|
137 |
+
value=0,
|
138 |
+
label="Seed Generator",
|
139 |
+
)
|
140 |
+
controlnet_mlsd_num_images_per_prompt = (
|
141 |
+
gr.Slider(
|
142 |
+
minimum=1,
|
143 |
+
maximum=10,
|
144 |
+
step=1,
|
145 |
+
value=1,
|
146 |
+
label="Number Of Images",
|
147 |
+
)
|
148 |
+
)
|
149 |
+
|
150 |
+
controlnet_mlsd_predict = gr.Button(value="Generator")
|
151 |
+
|
152 |
+
with gr.Column():
|
153 |
+
output_image = gr.Gallery(
|
154 |
+
label="Generated images",
|
155 |
+
show_label=False,
|
156 |
+
elem_id="gallery",
|
157 |
+
).style(grid=(1, 2))
|
158 |
+
|
159 |
+
controlnet_mlsd_predict.click(
|
160 |
+
fn=StableDiffusionControlNetMLSDGenerator().generate_image,
|
161 |
+
inputs=[
|
162 |
+
controlnet_mlsd_image_file,
|
163 |
+
controlnet_mlsd_model_id,
|
164 |
+
controlnet_mlsd_prompt,
|
165 |
+
controlnet_mlsd_negative_prompt,
|
166 |
+
controlnet_mlsd_num_images_per_prompt,
|
167 |
+
controlnet_mlsd_guidance_scale,
|
168 |
+
controlnet_mlsd_num_inference_step,
|
169 |
+
controlnet_mlsd_scheduler,
|
170 |
+
controlnet_mlsd_seed_generator,
|
171 |
+
],
|
172 |
+
outputs=output_image,
|
173 |
+
)
|
diffusion_webui/diffusion_models/controlnet/controlnet_pose.py
ADDED
@@ -0,0 +1,189 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
import torch
|
3 |
+
from controlnet_aux import OpenposeDetector
|
4 |
+
from diffusers import (
|
5 |
+
ControlNetModel,
|
6 |
+
StableDiffusionControlNetPipeline,
|
7 |
+
UniPCMultistepScheduler,
|
8 |
+
)
|
9 |
+
from PIL import Image
|
10 |
+
|
11 |
+
from diffusion_webui.utils.model_list import (
|
12 |
+
controlnet_pose_model_list,
|
13 |
+
stable_model_list,
|
14 |
+
)
|
15 |
+
from diffusion_webui.utils.scheduler_list import (
|
16 |
+
SCHEDULER_LIST,
|
17 |
+
get_scheduler_list,
|
18 |
+
)
|
19 |
+
|
20 |
+
|
21 |
+
class StableDiffusionControlNetPoseGenerator:
|
22 |
+
def __init__(self):
|
23 |
+
self.pipe = None
|
24 |
+
|
25 |
+
def load_model(self, stable_model_path, controlnet_model_path, scheduler):
|
26 |
+
if self.pipe is None:
|
27 |
+
controlnet = ControlNetModel.from_pretrained(
|
28 |
+
controlnet_model_path, torch_dtype=torch.float16
|
29 |
+
)
|
30 |
+
|
31 |
+
self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
|
32 |
+
pretrained_model_name_or_path=stable_model_path,
|
33 |
+
controlnet=controlnet,
|
34 |
+
safety_checker=None,
|
35 |
+
torch_dtype=torch.float16,
|
36 |
+
)
|
37 |
+
|
38 |
+
self.pipe = get_scheduler_list(pipe=self.pipe, scheduler=scheduler)
|
39 |
+
self.pipe.to("cuda")
|
40 |
+
self.pipe.enable_xformers_memory_efficient_attention()
|
41 |
+
|
42 |
+
return self.pipe
|
43 |
+
|
44 |
+
def controlnet_pose(self, image_path: str):
|
45 |
+
openpose = OpenposeDetector.from_pretrained("lllyasviel/ControlNet")
|
46 |
+
|
47 |
+
image = Image.open(image_path)
|
48 |
+
image = openpose(image)
|
49 |
+
|
50 |
+
return image
|
51 |
+
|
52 |
+
def generate_image(
|
53 |
+
self,
|
54 |
+
image_path: str,
|
55 |
+
stable_model_path: str,
|
56 |
+
controlnet_pose_model_path: str,
|
57 |
+
prompt: str,
|
58 |
+
negative_prompt: str,
|
59 |
+
num_images_per_prompt: int,
|
60 |
+
guidance_scale: int,
|
61 |
+
num_inference_step: int,
|
62 |
+
scheduler: str,
|
63 |
+
seed_generator: int,
|
64 |
+
):
|
65 |
+
|
66 |
+
image = self.controlnet_pose(image_path=image_path)
|
67 |
+
|
68 |
+
pipe = self.load_model(
|
69 |
+
stable_model_path=stable_model_path,
|
70 |
+
controlnet_model_path=controlnet_pose_model_path,
|
71 |
+
scheduler=scheduler,
|
72 |
+
)
|
73 |
+
|
74 |
+
if seed_generator == 0:
|
75 |
+
random_seed = torch.randint(0, 1000000, (1,))
|
76 |
+
generator = torch.manual_seed(random_seed)
|
77 |
+
else:
|
78 |
+
generator = torch.manual_seed(seed_generator)
|
79 |
+
|
80 |
+
output = pipe(
|
81 |
+
prompt=prompt,
|
82 |
+
image=image,
|
83 |
+
negative_prompt=negative_prompt,
|
84 |
+
num_images_per_prompt=num_images_per_prompt,
|
85 |
+
num_inference_steps=num_inference_step,
|
86 |
+
guidance_scale=guidance_scale,
|
87 |
+
generator=generator,
|
88 |
+
).images
|
89 |
+
|
90 |
+
return output
|
91 |
+
|
92 |
+
def app():
|
93 |
+
with gr.Blocks():
|
94 |
+
with gr.Row():
|
95 |
+
with gr.Column():
|
96 |
+
controlnet_pose_image_file = gr.Image(
|
97 |
+
type="filepath", label="Image"
|
98 |
+
)
|
99 |
+
|
100 |
+
controlnet_pose_prompt = gr.Textbox(
|
101 |
+
lines=1,
|
102 |
+
show_label=False,
|
103 |
+
placeholder="Prompt",
|
104 |
+
)
|
105 |
+
|
106 |
+
controlnet_pose_negative_prompt = gr.Textbox(
|
107 |
+
lines=1,
|
108 |
+
show_label=False,
|
109 |
+
placeholder="Negative Prompt",
|
110 |
+
)
|
111 |
+
|
112 |
+
with gr.Row():
|
113 |
+
with gr.Column():
|
114 |
+
controlnet_pose_stable_model_id = gr.Dropdown(
|
115 |
+
choices=stable_model_list,
|
116 |
+
value=stable_model_list[0],
|
117 |
+
label="Stable Model Id",
|
118 |
+
)
|
119 |
+
controlnet_pose_guidance_scale = gr.Slider(
|
120 |
+
minimum=0.1,
|
121 |
+
maximum=15,
|
122 |
+
step=0.1,
|
123 |
+
value=7.5,
|
124 |
+
label="Guidance Scale",
|
125 |
+
)
|
126 |
+
|
127 |
+
controlnet_pose_num_inference_step = gr.Slider(
|
128 |
+
minimum=1,
|
129 |
+
maximum=100,
|
130 |
+
step=1,
|
131 |
+
value=50,
|
132 |
+
label="Num Inference Step",
|
133 |
+
)
|
134 |
+
|
135 |
+
controlnet_pose_num_images_per_prompt = gr.Slider(
|
136 |
+
minimum=1,
|
137 |
+
maximum=10,
|
138 |
+
step=1,
|
139 |
+
value=1,
|
140 |
+
label="Number Of Images",
|
141 |
+
)
|
142 |
+
|
143 |
+
with gr.Row():
|
144 |
+
with gr.Column():
|
145 |
+
controlnet_pose_model_id = gr.Dropdown(
|
146 |
+
choices=controlnet_pose_model_list,
|
147 |
+
value=controlnet_pose_model_list[0],
|
148 |
+
label="ControlNet Model Id",
|
149 |
+
)
|
150 |
+
|
151 |
+
controlnet_pose_scheduler = gr.Dropdown(
|
152 |
+
choices=SCHEDULER_LIST,
|
153 |
+
value=SCHEDULER_LIST[0],
|
154 |
+
label="Scheduler",
|
155 |
+
)
|
156 |
+
|
157 |
+
controlnet_pose_seed_generator = gr.Number(
|
158 |
+
minimum=0,
|
159 |
+
maximum=1000000,
|
160 |
+
step=1,
|
161 |
+
value=0,
|
162 |
+
label="Seed Generator",
|
163 |
+
)
|
164 |
+
|
165 |
+
controlnet_pose_predict = gr.Button(value="Generator")
|
166 |
+
|
167 |
+
with gr.Column():
|
168 |
+
output_image = gr.Gallery(
|
169 |
+
label="Generated images",
|
170 |
+
show_label=False,
|
171 |
+
elem_id="gallery",
|
172 |
+
).style(grid=(1, 2))
|
173 |
+
|
174 |
+
controlnet_pose_predict.click(
|
175 |
+
fn=StableDiffusionControlNetPoseGenerator().generate_image,
|
176 |
+
inputs=[
|
177 |
+
controlnet_pose_image_file,
|
178 |
+
controlnet_pose_stable_model_id,
|
179 |
+
controlnet_pose_model_id,
|
180 |
+
controlnet_pose_prompt,
|
181 |
+
controlnet_pose_negative_prompt,
|
182 |
+
controlnet_pose_num_images_per_prompt,
|
183 |
+
controlnet_pose_guidance_scale,
|
184 |
+
controlnet_pose_num_inference_step,
|
185 |
+
controlnet_pose_scheduler,
|
186 |
+
controlnet_pose_seed_generator,
|
187 |
+
],
|
188 |
+
outputs=output_image,
|
189 |
+
)
|
diffusion_webui/diffusion_models/controlnet/controlnet_scribble.py
ADDED
@@ -0,0 +1,188 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
import torch
|
3 |
+
from controlnet_aux import HEDdetector
|
4 |
+
from diffusers import (
|
5 |
+
ControlNetModel,
|
6 |
+
StableDiffusionControlNetPipeline,
|
7 |
+
UniPCMultistepScheduler,
|
8 |
+
)
|
9 |
+
from PIL import Image
|
10 |
+
|
11 |
+
from diffusion_webui.utils.model_list import (
|
12 |
+
controlnet_scribble_model_list,
|
13 |
+
stable_model_list,
|
14 |
+
)
|
15 |
+
from diffusion_webui.utils.scheduler_list import (
|
16 |
+
SCHEDULER_LIST,
|
17 |
+
get_scheduler_list,
|
18 |
+
)
|
19 |
+
|
20 |
+
|
21 |
+
class StableDiffusionControlNetScribbleGenerator:
|
22 |
+
def __init__(self):
|
23 |
+
self.pipe = None
|
24 |
+
|
25 |
+
def load_model(self, stable_model_path, controlnet_model_path, scheduler):
|
26 |
+
if self.pipe is None:
|
27 |
+
controlnet = ControlNetModel.from_pretrained(
|
28 |
+
controlnet_model_path, torch_dtype=torch.float16
|
29 |
+
)
|
30 |
+
|
31 |
+
self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
|
32 |
+
pretrained_model_name_or_path=stable_model_path,
|
33 |
+
controlnet=controlnet,
|
34 |
+
safety_checker=None,
|
35 |
+
torch_dtype=torch.float16,
|
36 |
+
)
|
37 |
+
|
38 |
+
self.pipe = get_scheduler_list(pipe=self.pipe, scheduler=scheduler)
|
39 |
+
self.pipe.to("cuda")
|
40 |
+
self.pipe.enable_xformers_memory_efficient_attention()
|
41 |
+
|
42 |
+
return self.pipe
|
43 |
+
|
44 |
+
def controlnet_scribble(self, image_path: str):
|
45 |
+
hed = HEDdetector.from_pretrained("lllyasviel/ControlNet")
|
46 |
+
|
47 |
+
image = Image.open(image_path)
|
48 |
+
image = hed(image, scribble=True)
|
49 |
+
|
50 |
+
return image
|
51 |
+
|
52 |
+
def generate_image(
|
53 |
+
self,
|
54 |
+
image_path: str,
|
55 |
+
stable_model_path: str,
|
56 |
+
controlnet_hed_model_path: str,
|
57 |
+
prompt: str,
|
58 |
+
negative_prompt: str,
|
59 |
+
num_images_per_prompt: int,
|
60 |
+
guidance_scale: int,
|
61 |
+
num_inference_step: int,
|
62 |
+
scheduler: str,
|
63 |
+
seed_generator: int,
|
64 |
+
):
|
65 |
+
|
66 |
+
image = self.controlnet_scribble(image_path=image_path)
|
67 |
+
|
68 |
+
pipe = self.load_model(
|
69 |
+
stable_model_path=stable_model_path,
|
70 |
+
controlnet_model_path=controlnet_hed_model_path,
|
71 |
+
scheduler=scheduler,
|
72 |
+
)
|
73 |
+
if seed_generator == 0:
|
74 |
+
random_seed = torch.randint(0, 1000000, (1,))
|
75 |
+
generator = torch.manual_seed(random_seed)
|
76 |
+
else:
|
77 |
+
generator = torch.manual_seed(seed_generator)
|
78 |
+
|
79 |
+
output = pipe(
|
80 |
+
prompt=prompt,
|
81 |
+
image=image,
|
82 |
+
negative_prompt=negative_prompt,
|
83 |
+
num_images_per_prompt=num_images_per_prompt,
|
84 |
+
num_inference_steps=num_inference_step,
|
85 |
+
guidance_scale=guidance_scale,
|
86 |
+
generator=generator,
|
87 |
+
).images
|
88 |
+
|
89 |
+
return output
|
90 |
+
|
91 |
+
def app():
|
92 |
+
with gr.Blocks():
|
93 |
+
with gr.Row():
|
94 |
+
with gr.Column():
|
95 |
+
controlnet_scribble_image_file = gr.Image(
|
96 |
+
type="filepath", label="Image"
|
97 |
+
)
|
98 |
+
controlnet_scribble_prompt = gr.Textbox(
|
99 |
+
lines=1,
|
100 |
+
show_label=False,
|
101 |
+
placeholder="Prompt",
|
102 |
+
)
|
103 |
+
|
104 |
+
controlnet_scribble_negative_prompt = gr.Textbox(
|
105 |
+
lines=1,
|
106 |
+
show_label=False,
|
107 |
+
placeholder="Negative Prompt",
|
108 |
+
)
|
109 |
+
|
110 |
+
with gr.Row():
|
111 |
+
with gr.Column():
|
112 |
+
controlnet_scribble_stable_model_id = gr.Dropdown(
|
113 |
+
choices=stable_model_list,
|
114 |
+
value=stable_model_list[0],
|
115 |
+
label="Stable Model Id",
|
116 |
+
)
|
117 |
+
controlnet_scribble_guidance_scale = gr.Slider(
|
118 |
+
minimum=0.1,
|
119 |
+
maximum=15,
|
120 |
+
step=0.1,
|
121 |
+
value=7.5,
|
122 |
+
label="Guidance Scale",
|
123 |
+
)
|
124 |
+
|
125 |
+
controlnet_scribble_num_inference_step = gr.Slider(
|
126 |
+
minimum=1,
|
127 |
+
maximum=100,
|
128 |
+
step=1,
|
129 |
+
value=50,
|
130 |
+
label="Num Inference Step",
|
131 |
+
)
|
132 |
+
|
133 |
+
controlnet_scribble_num_images_per_prompt = (
|
134 |
+
gr.Slider(
|
135 |
+
minimum=1,
|
136 |
+
maximum=10,
|
137 |
+
step=1,
|
138 |
+
value=1,
|
139 |
+
label="Number Of Images",
|
140 |
+
)
|
141 |
+
)
|
142 |
+
with gr.Row():
|
143 |
+
with gr.Column():
|
144 |
+
controlnet_scribble_model_id = gr.Dropdown(
|
145 |
+
choices=controlnet_scribble_model_list,
|
146 |
+
value=controlnet_scribble_model_list[0],
|
147 |
+
label="ControlNet Model Id",
|
148 |
+
)
|
149 |
+
|
150 |
+
controlnet_scribble_scheduler = gr.Dropdown(
|
151 |
+
choices=SCHEDULER_LIST,
|
152 |
+
value=SCHEDULER_LIST[0],
|
153 |
+
label="Scheduler",
|
154 |
+
)
|
155 |
+
|
156 |
+
controlnet_scribble_seed_generator = gr.Number(
|
157 |
+
minimum=0,
|
158 |
+
maximum=1000000,
|
159 |
+
step=1,
|
160 |
+
value=0,
|
161 |
+
label="Seed Generator",
|
162 |
+
)
|
163 |
+
|
164 |
+
controlnet_scribble_predict = gr.Button(value="Generator")
|
165 |
+
|
166 |
+
with gr.Column():
|
167 |
+
output_image = gr.Gallery(
|
168 |
+
label="Generated images",
|
169 |
+
show_label=False,
|
170 |
+
elem_id="gallery",
|
171 |
+
).style(grid=(1, 2))
|
172 |
+
|
173 |
+
controlnet_scribble_predict.click(
|
174 |
+
fn=StableDiffusionControlNetScribbleGenerator().generate_image,
|
175 |
+
inputs=[
|
176 |
+
controlnet_scribble_image_file,
|
177 |
+
controlnet_scribble_stable_model_id,
|
178 |
+
controlnet_scribble_model_id,
|
179 |
+
controlnet_scribble_prompt,
|
180 |
+
controlnet_scribble_negative_prompt,
|
181 |
+
controlnet_scribble_num_images_per_prompt,
|
182 |
+
controlnet_scribble_guidance_scale,
|
183 |
+
controlnet_scribble_num_inference_step,
|
184 |
+
controlnet_scribble_scheduler,
|
185 |
+
controlnet_scribble_seed_generator,
|
186 |
+
],
|
187 |
+
outputs=output_image,
|
188 |
+
)
|
diffusion_webui/diffusion_models/controlnet/controlnet_seg.py
ADDED
@@ -0,0 +1,353 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
import numpy as np
|
3 |
+
import torch
|
4 |
+
from diffusers import ControlNetModel, StableDiffusionControlNetPipeline
|
5 |
+
from PIL import Image
|
6 |
+
from transformers import AutoImageProcessor, UperNetForSemanticSegmentation
|
7 |
+
|
8 |
+
from diffusion_webui.utils.model_list import stable_model_list
|
9 |
+
from diffusion_webui.utils.scheduler_list import (
|
10 |
+
SCHEDULER_LIST,
|
11 |
+
get_scheduler_list,
|
12 |
+
)
|
13 |
+
|
14 |
+
|
15 |
+
def ade_palette():
|
16 |
+
"""ADE20K palette that maps each class to RGB values."""
|
17 |
+
return [
|
18 |
+
[120, 120, 120],
|
19 |
+
[180, 120, 120],
|
20 |
+
[6, 230, 230],
|
21 |
+
[80, 50, 50],
|
22 |
+
[4, 200, 3],
|
23 |
+
[120, 120, 80],
|
24 |
+
[140, 140, 140],
|
25 |
+
[204, 5, 255],
|
26 |
+
[230, 230, 230],
|
27 |
+
[4, 250, 7],
|
28 |
+
[224, 5, 255],
|
29 |
+
[235, 255, 7],
|
30 |
+
[150, 5, 61],
|
31 |
+
[120, 120, 70],
|
32 |
+
[8, 255, 51],
|
33 |
+
[255, 6, 82],
|
34 |
+
[143, 255, 140],
|
35 |
+
[204, 255, 4],
|
36 |
+
[255, 51, 7],
|
37 |
+
[204, 70, 3],
|
38 |
+
[0, 102, 200],
|
39 |
+
[61, 230, 250],
|
40 |
+
[255, 6, 51],
|
41 |
+
[11, 102, 255],
|
42 |
+
[255, 7, 71],
|
43 |
+
[255, 9, 224],
|
44 |
+
[9, 7, 230],
|
45 |
+
[220, 220, 220],
|
46 |
+
[255, 9, 92],
|
47 |
+
[112, 9, 255],
|
48 |
+
[8, 255, 214],
|
49 |
+
[7, 255, 224],
|
50 |
+
[255, 184, 6],
|
51 |
+
[10, 255, 71],
|
52 |
+
[255, 41, 10],
|
53 |
+
[7, 255, 255],
|
54 |
+
[224, 255, 8],
|
55 |
+
[102, 8, 255],
|
56 |
+
[255, 61, 6],
|
57 |
+
[255, 194, 7],
|
58 |
+
[255, 122, 8],
|
59 |
+
[0, 255, 20],
|
60 |
+
[255, 8, 41],
|
61 |
+
[255, 5, 153],
|
62 |
+
[6, 51, 255],
|
63 |
+
[235, 12, 255],
|
64 |
+
[160, 150, 20],
|
65 |
+
[0, 163, 255],
|
66 |
+
[140, 140, 140],
|
67 |
+
[250, 10, 15],
|
68 |
+
[20, 255, 0],
|
69 |
+
[31, 255, 0],
|
70 |
+
[255, 31, 0],
|
71 |
+
[255, 224, 0],
|
72 |
+
[153, 255, 0],
|
73 |
+
[0, 0, 255],
|
74 |
+
[255, 71, 0],
|
75 |
+
[0, 235, 255],
|
76 |
+
[0, 173, 255],
|
77 |
+
[31, 0, 255],
|
78 |
+
[11, 200, 200],
|
79 |
+
[255, 82, 0],
|
80 |
+
[0, 255, 245],
|
81 |
+
[0, 61, 255],
|
82 |
+
[0, 255, 112],
|
83 |
+
[0, 255, 133],
|
84 |
+
[255, 0, 0],
|
85 |
+
[255, 163, 0],
|
86 |
+
[255, 102, 0],
|
87 |
+
[194, 255, 0],
|
88 |
+
[0, 143, 255],
|
89 |
+
[51, 255, 0],
|
90 |
+
[0, 82, 255],
|
91 |
+
[0, 255, 41],
|
92 |
+
[0, 255, 173],
|
93 |
+
[10, 0, 255],
|
94 |
+
[173, 255, 0],
|
95 |
+
[0, 255, 153],
|
96 |
+
[255, 92, 0],
|
97 |
+
[255, 0, 255],
|
98 |
+
[255, 0, 245],
|
99 |
+
[255, 0, 102],
|
100 |
+
[255, 173, 0],
|
101 |
+
[255, 0, 20],
|
102 |
+
[255, 184, 184],
|
103 |
+
[0, 31, 255],
|
104 |
+
[0, 255, 61],
|
105 |
+
[0, 71, 255],
|
106 |
+
[255, 0, 204],
|
107 |
+
[0, 255, 194],
|
108 |
+
[0, 255, 82],
|
109 |
+
[0, 10, 255],
|
110 |
+
[0, 112, 255],
|
111 |
+
[51, 0, 255],
|
112 |
+
[0, 194, 255],
|
113 |
+
[0, 122, 255],
|
114 |
+
[0, 255, 163],
|
115 |
+
[255, 153, 0],
|
116 |
+
[0, 255, 10],
|
117 |
+
[255, 112, 0],
|
118 |
+
[143, 255, 0],
|
119 |
+
[82, 0, 255],
|
120 |
+
[163, 255, 0],
|
121 |
+
[255, 235, 0],
|
122 |
+
[8, 184, 170],
|
123 |
+
[133, 0, 255],
|
124 |
+
[0, 255, 92],
|
125 |
+
[184, 0, 255],
|
126 |
+
[255, 0, 31],
|
127 |
+
[0, 184, 255],
|
128 |
+
[0, 214, 255],
|
129 |
+
[255, 0, 112],
|
130 |
+
[92, 255, 0],
|
131 |
+
[0, 224, 255],
|
132 |
+
[112, 224, 255],
|
133 |
+
[70, 184, 160],
|
134 |
+
[163, 0, 255],
|
135 |
+
[153, 0, 255],
|
136 |
+
[71, 255, 0],
|
137 |
+
[255, 0, 163],
|
138 |
+
[255, 204, 0],
|
139 |
+
[255, 0, 143],
|
140 |
+
[0, 255, 235],
|
141 |
+
[133, 255, 0],
|
142 |
+
[255, 0, 235],
|
143 |
+
[245, 0, 255],
|
144 |
+
[255, 0, 122],
|
145 |
+
[255, 245, 0],
|
146 |
+
[10, 190, 212],
|
147 |
+
[214, 255, 0],
|
148 |
+
[0, 204, 255],
|
149 |
+
[20, 0, 255],
|
150 |
+
[255, 255, 0],
|
151 |
+
[0, 153, 255],
|
152 |
+
[0, 41, 255],
|
153 |
+
[0, 255, 204],
|
154 |
+
[41, 0, 255],
|
155 |
+
[41, 255, 0],
|
156 |
+
[173, 0, 255],
|
157 |
+
[0, 245, 255],
|
158 |
+
[71, 0, 255],
|
159 |
+
[122, 0, 255],
|
160 |
+
[0, 255, 184],
|
161 |
+
[0, 92, 255],
|
162 |
+
[184, 255, 0],
|
163 |
+
[0, 133, 255],
|
164 |
+
[255, 214, 0],
|
165 |
+
[25, 194, 194],
|
166 |
+
[102, 255, 0],
|
167 |
+
[92, 0, 255],
|
168 |
+
]
|
169 |
+
|
170 |
+
|
171 |
+
class StableDiffusionControlNetSegGenerator:
|
172 |
+
def __init__(self):
|
173 |
+
self.pipe = None
|
174 |
+
|
175 |
+
def load_model(
|
176 |
+
self,
|
177 |
+
stable_model_path,
|
178 |
+
scheduler,
|
179 |
+
):
|
180 |
+
|
181 |
+
if self.pipe is None:
|
182 |
+
controlnet = ControlNetModel.from_pretrained(
|
183 |
+
"lllyasviel/sd-controlnet-seg", torch_dtype=torch.float16
|
184 |
+
)
|
185 |
+
self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
|
186 |
+
pretrained_model_name_or_path=stable_model_path,
|
187 |
+
controlnet=controlnet,
|
188 |
+
safety_checker=None,
|
189 |
+
torch_dtype=torch.float16,
|
190 |
+
)
|
191 |
+
|
192 |
+
self.pipe = get_scheduler_list(pipe=self.pipe, scheduler=scheduler)
|
193 |
+
self.pipe.to("cuda")
|
194 |
+
self.pipe.enable_xformers_memory_efficient_attention()
|
195 |
+
|
196 |
+
return self.pipe
|
197 |
+
|
198 |
+
def controlnet_seg(self, image_path: str):
|
199 |
+
image_processor = AutoImageProcessor.from_pretrained(
|
200 |
+
"openmmlab/upernet-convnext-small"
|
201 |
+
)
|
202 |
+
image_segmentor = UperNetForSemanticSegmentation.from_pretrained(
|
203 |
+
"openmmlab/upernet-convnext-small"
|
204 |
+
)
|
205 |
+
|
206 |
+
image = Image.open(image_path).convert("RGB")
|
207 |
+
pixel_values = image_processor(image, return_tensors="pt").pixel_values
|
208 |
+
|
209 |
+
with torch.no_grad():
|
210 |
+
outputs = image_segmentor(pixel_values)
|
211 |
+
|
212 |
+
seg = image_processor.post_process_semantic_segmentation(
|
213 |
+
outputs, target_sizes=[image.size[::-1]]
|
214 |
+
)[0]
|
215 |
+
|
216 |
+
color_seg = np.zeros((seg.shape[0], seg.shape[1], 3), dtype=np.uint8)
|
217 |
+
palette = np.array(ade_palette())
|
218 |
+
|
219 |
+
for label, color in enumerate(palette):
|
220 |
+
color_seg[seg == label, :] = color
|
221 |
+
|
222 |
+
color_seg = color_seg.astype(np.uint8)
|
223 |
+
image = Image.fromarray(color_seg)
|
224 |
+
|
225 |
+
return image
|
226 |
+
|
227 |
+
def generate_image(
|
228 |
+
self,
|
229 |
+
image_path: str,
|
230 |
+
model_path: str,
|
231 |
+
prompt: str,
|
232 |
+
negative_prompt: str,
|
233 |
+
num_images_per_prompt: int,
|
234 |
+
guidance_scale: int,
|
235 |
+
num_inference_step: int,
|
236 |
+
scheduler: str,
|
237 |
+
seed_generator: int,
|
238 |
+
):
|
239 |
+
|
240 |
+
image = self.controlnet_seg(image_path=image_path)
|
241 |
+
pipe = self.load_model(
|
242 |
+
stable_model_path=model_path,
|
243 |
+
scheduler=scheduler,
|
244 |
+
)
|
245 |
+
if seed_generator == 0:
|
246 |
+
random_seed = torch.randint(0, 1000000, (1,))
|
247 |
+
generator = torch.manual_seed(random_seed)
|
248 |
+
else:
|
249 |
+
generator = torch.manual_seed(seed_generator)
|
250 |
+
|
251 |
+
output = pipe(
|
252 |
+
prompt=prompt,
|
253 |
+
image=image,
|
254 |
+
negative_prompt=negative_prompt,
|
255 |
+
num_images_per_prompt=num_images_per_prompt,
|
256 |
+
num_inference_steps=num_inference_step,
|
257 |
+
guidance_scale=guidance_scale,
|
258 |
+
generator=generator,
|
259 |
+
).images
|
260 |
+
|
261 |
+
return output
|
262 |
+
|
263 |
+
def app():
|
264 |
+
with gr.Blocks():
|
265 |
+
with gr.Row():
|
266 |
+
with gr.Column():
|
267 |
+
controlnet_seg_image_file = gr.Image(
|
268 |
+
type="filepath", label="Image"
|
269 |
+
)
|
270 |
+
|
271 |
+
controlnet_seg_prompt = gr.Textbox(
|
272 |
+
lines=1,
|
273 |
+
show_label=False,
|
274 |
+
placeholder="Prompt",
|
275 |
+
)
|
276 |
+
|
277 |
+
controlnet_seg_negative_prompt = gr.Textbox(
|
278 |
+
lines=1,
|
279 |
+
show_label=False,
|
280 |
+
placeholder="Negative Prompt",
|
281 |
+
)
|
282 |
+
|
283 |
+
with gr.Row():
|
284 |
+
with gr.Column():
|
285 |
+
controlnet_seg_model_id = gr.Dropdown(
|
286 |
+
choices=stable_model_list,
|
287 |
+
value=stable_model_list[0],
|
288 |
+
label="Stable Model Id",
|
289 |
+
)
|
290 |
+
controlnet_seg_guidance_scale = gr.Slider(
|
291 |
+
minimum=0.1,
|
292 |
+
maximum=15,
|
293 |
+
step=0.1,
|
294 |
+
value=7.5,
|
295 |
+
label="Guidance Scale",
|
296 |
+
)
|
297 |
+
|
298 |
+
controlnet_seg_num_inference_step = gr.Slider(
|
299 |
+
minimum=1,
|
300 |
+
maximum=100,
|
301 |
+
step=1,
|
302 |
+
value=50,
|
303 |
+
label="Num Inference Step",
|
304 |
+
)
|
305 |
+
|
306 |
+
with gr.Row():
|
307 |
+
with gr.Column():
|
308 |
+
controlnet_seg_scheduler = gr.Dropdown(
|
309 |
+
choices=SCHEDULER_LIST,
|
310 |
+
value=SCHEDULER_LIST[0],
|
311 |
+
label="Scheduler",
|
312 |
+
)
|
313 |
+
controlnet_seg_num_images_per_prompt = (
|
314 |
+
gr.Slider(
|
315 |
+
minimum=1,
|
316 |
+
maximum=10,
|
317 |
+
step=1,
|
318 |
+
value=1,
|
319 |
+
label="Number Of Images",
|
320 |
+
)
|
321 |
+
)
|
322 |
+
controlnet_seg_seed_generator = gr.Slider(
|
323 |
+
minimum=0,
|
324 |
+
maximum=1000000,
|
325 |
+
step=1,
|
326 |
+
value=0,
|
327 |
+
label="Seed Generator",
|
328 |
+
)
|
329 |
+
|
330 |
+
controlnet_seg_predict = gr.Button(value="Generator")
|
331 |
+
|
332 |
+
with gr.Column():
|
333 |
+
output_image = gr.Gallery(
|
334 |
+
label="Generated images",
|
335 |
+
show_label=False,
|
336 |
+
elem_id="gallery",
|
337 |
+
).style(grid=(1, 2))
|
338 |
+
|
339 |
+
controlnet_seg_predict.click(
|
340 |
+
fn=StableDiffusionControlNetSegGenerator().generate_image,
|
341 |
+
inputs=[
|
342 |
+
controlnet_seg_image_file,
|
343 |
+
controlnet_seg_model_id,
|
344 |
+
controlnet_seg_prompt,
|
345 |
+
controlnet_seg_negative_prompt,
|
346 |
+
controlnet_seg_num_images_per_prompt,
|
347 |
+
controlnet_seg_guidance_scale,
|
348 |
+
controlnet_seg_num_inference_step,
|
349 |
+
controlnet_seg_scheduler,
|
350 |
+
controlnet_seg_seed_generator,
|
351 |
+
],
|
352 |
+
outputs=[output_image],
|
353 |
+
)
|
diffusion_webui/diffusion_models/stable_diffusion/__init__.py
ADDED
File without changes
|
diffusion_webui/diffusion_models/stable_diffusion/__pycache__/__init__.cpython-38.pyc
ADDED
Binary file (215 Bytes). View file
|
|
diffusion_webui/diffusion_models/stable_diffusion/__pycache__/img2img_app.cpython-38.pyc
ADDED
Binary file (3.48 kB). View file
|
|
diffusion_webui/diffusion_models/stable_diffusion/__pycache__/inpaint_app.cpython-38.pyc
ADDED
Binary file (3.44 kB). View file
|
|
diffusion_webui/diffusion_models/stable_diffusion/__pycache__/text2img_app.cpython-38.pyc
ADDED
Binary file (3.52 kB). View file
|
|
diffusion_webui/diffusion_models/stable_diffusion/img2img_app.py
ADDED
@@ -0,0 +1,153 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
import torch
|
3 |
+
from diffusers import StableDiffusionImg2ImgPipeline
|
4 |
+
from PIL import Image
|
5 |
+
|
6 |
+
from diffusion_webui.utils.model_list import stable_model_list
|
7 |
+
from diffusion_webui.utils.scheduler_list import (
|
8 |
+
SCHEDULER_LIST,
|
9 |
+
get_scheduler_list,
|
10 |
+
)
|
11 |
+
|
12 |
+
|
13 |
+
class StableDiffusionImage2ImageGenerator:
|
14 |
+
def __init__(self):
|
15 |
+
self.pipe = None
|
16 |
+
|
17 |
+
def load_model(self, model_path, scheduler):
|
18 |
+
if self.pipe is None:
|
19 |
+
self.pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
|
20 |
+
model_path, safety_checker=None, torch_dtype=torch.float16
|
21 |
+
)
|
22 |
+
|
23 |
+
self.pipe = get_scheduler_list(pipe=self.pipe, scheduler=scheduler)
|
24 |
+
self.pipe.to("cuda")
|
25 |
+
self.pipe.enable_xformers_memory_efficient_attention()
|
26 |
+
|
27 |
+
return self.pipe
|
28 |
+
|
29 |
+
def generate_image(
|
30 |
+
self,
|
31 |
+
image_path: str,
|
32 |
+
model_path: str,
|
33 |
+
prompt: str,
|
34 |
+
negative_prompt: str,
|
35 |
+
num_images_per_prompt: int,
|
36 |
+
scheduler: str,
|
37 |
+
guidance_scale: int,
|
38 |
+
num_inference_step: int,
|
39 |
+
seed_generator=0,
|
40 |
+
):
|
41 |
+
pipe = self.load_model(
|
42 |
+
model_path=model_path,
|
43 |
+
scheduler=scheduler,
|
44 |
+
)
|
45 |
+
|
46 |
+
if seed_generator == 0:
|
47 |
+
random_seed = torch.randint(0, 1000000, (1,))
|
48 |
+
generator = torch.manual_seed(random_seed)
|
49 |
+
else:
|
50 |
+
generator = torch.manual_seed(seed_generator)
|
51 |
+
|
52 |
+
image = Image.open(image_path)
|
53 |
+
images = pipe(
|
54 |
+
prompt,
|
55 |
+
image=image,
|
56 |
+
negative_prompt=negative_prompt,
|
57 |
+
num_images_per_prompt=num_images_per_prompt,
|
58 |
+
num_inference_steps=num_inference_step,
|
59 |
+
guidance_scale=guidance_scale,
|
60 |
+
generator=generator,
|
61 |
+
).images
|
62 |
+
|
63 |
+
return images
|
64 |
+
|
65 |
+
def app():
|
66 |
+
with gr.Blocks():
|
67 |
+
with gr.Row():
|
68 |
+
with gr.Column():
|
69 |
+
image2image_image_file = gr.Image(
|
70 |
+
type="filepath", label="Image"
|
71 |
+
).style(height=260)
|
72 |
+
|
73 |
+
image2image_prompt = gr.Textbox(
|
74 |
+
lines=1,
|
75 |
+
placeholder="Prompt",
|
76 |
+
show_label=False,
|
77 |
+
)
|
78 |
+
|
79 |
+
image2image_negative_prompt = gr.Textbox(
|
80 |
+
lines=1,
|
81 |
+
placeholder="Negative Prompt",
|
82 |
+
show_label=False,
|
83 |
+
)
|
84 |
+
|
85 |
+
with gr.Row():
|
86 |
+
with gr.Column():
|
87 |
+
image2image_model_path = gr.Dropdown(
|
88 |
+
choices=stable_model_list,
|
89 |
+
value=stable_model_list[0],
|
90 |
+
label="Stable Model Id",
|
91 |
+
)
|
92 |
+
|
93 |
+
image2image_guidance_scale = gr.Slider(
|
94 |
+
minimum=0.1,
|
95 |
+
maximum=15,
|
96 |
+
step=0.1,
|
97 |
+
value=7.5,
|
98 |
+
label="Guidance Scale",
|
99 |
+
)
|
100 |
+
image2image_num_inference_step = gr.Slider(
|
101 |
+
minimum=1,
|
102 |
+
maximum=100,
|
103 |
+
step=1,
|
104 |
+
value=50,
|
105 |
+
label="Num Inference Step",
|
106 |
+
)
|
107 |
+
with gr.Row():
|
108 |
+
with gr.Column():
|
109 |
+
image2image_scheduler = gr.Dropdown(
|
110 |
+
choices=SCHEDULER_LIST,
|
111 |
+
value=SCHEDULER_LIST[0],
|
112 |
+
label="Scheduler",
|
113 |
+
)
|
114 |
+
image2image_num_images_per_prompt = gr.Slider(
|
115 |
+
minimum=1,
|
116 |
+
maximum=30,
|
117 |
+
step=1,
|
118 |
+
value=1,
|
119 |
+
label="Number Of Images",
|
120 |
+
)
|
121 |
+
|
122 |
+
image2image_seed_generator = gr.Slider(
|
123 |
+
minimum=0,
|
124 |
+
maximum=1000000,
|
125 |
+
step=1,
|
126 |
+
value=0,
|
127 |
+
label="Seed(0 for random)",
|
128 |
+
)
|
129 |
+
|
130 |
+
image2image_predict_button = gr.Button(value="Generator")
|
131 |
+
|
132 |
+
with gr.Column():
|
133 |
+
output_image = gr.Gallery(
|
134 |
+
label="Generated images",
|
135 |
+
show_label=False,
|
136 |
+
elem_id="gallery",
|
137 |
+
).style(grid=(1, 2))
|
138 |
+
|
139 |
+
image2image_predict_button.click(
|
140 |
+
fn=StableDiffusionImage2ImageGenerator().generate_image,
|
141 |
+
inputs=[
|
142 |
+
image2image_image_file,
|
143 |
+
image2image_model_path,
|
144 |
+
image2image_prompt,
|
145 |
+
image2image_negative_prompt,
|
146 |
+
image2image_num_images_per_prompt,
|
147 |
+
image2image_scheduler,
|
148 |
+
image2image_guidance_scale,
|
149 |
+
image2image_num_inference_step,
|
150 |
+
image2image_seed_generator,
|
151 |
+
],
|
152 |
+
outputs=[output_image],
|
153 |
+
)
|
diffusion_webui/diffusion_models/stable_diffusion/inpaint_app.py
ADDED
@@ -0,0 +1,148 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
import torch
|
3 |
+
from diffusers import DiffusionPipeline
|
4 |
+
|
5 |
+
from diffusion_webui.utils.model_list import stable_inpiant_model_list
|
6 |
+
|
7 |
+
|
8 |
+
class StableDiffusionInpaintGenerator:
|
9 |
+
def __init__(self):
|
10 |
+
self.pipe = None
|
11 |
+
|
12 |
+
def load_model(self, model_path):
|
13 |
+
if self.pipe is None:
|
14 |
+
self.pipe = DiffusionPipeline.from_pretrained(
|
15 |
+
model_path, revision="fp16", torch_dtype=torch.float16
|
16 |
+
)
|
17 |
+
|
18 |
+
self.pipe.to("cuda")
|
19 |
+
self.pipe.enable_xformers_memory_efficient_attention()
|
20 |
+
|
21 |
+
return self.pipe
|
22 |
+
|
23 |
+
def generate_image(
|
24 |
+
self,
|
25 |
+
pil_image: str,
|
26 |
+
model_path: str,
|
27 |
+
prompt: str,
|
28 |
+
negative_prompt: str,
|
29 |
+
num_images_per_prompt: int,
|
30 |
+
guidance_scale: int,
|
31 |
+
num_inference_step: int,
|
32 |
+
seed_generator=0,
|
33 |
+
):
|
34 |
+
image = pil_image["image"].convert("RGB").resize((512, 512))
|
35 |
+
mask_image = pil_image["mask"].convert("RGB").resize((512, 512))
|
36 |
+
pipe = self.load_model(model_path)
|
37 |
+
|
38 |
+
if seed_generator == 0:
|
39 |
+
random_seed = torch.randint(0, 1000000, (1,))
|
40 |
+
generator = torch.manual_seed(random_seed)
|
41 |
+
else:
|
42 |
+
generator = torch.manual_seed(seed_generator)
|
43 |
+
|
44 |
+
output = pipe(
|
45 |
+
prompt=prompt,
|
46 |
+
image=image,
|
47 |
+
mask_image=mask_image,
|
48 |
+
negative_prompt=negative_prompt,
|
49 |
+
num_images_per_prompt=num_images_per_prompt,
|
50 |
+
num_inference_steps=num_inference_step,
|
51 |
+
guidance_scale=guidance_scale,
|
52 |
+
generator=generator,
|
53 |
+
).images
|
54 |
+
|
55 |
+
return output
|
56 |
+
|
57 |
+
def app():
|
58 |
+
with gr.Blocks():
|
59 |
+
with gr.Row():
|
60 |
+
with gr.Column():
|
61 |
+
stable_diffusion_inpaint_image_file = gr.Image(
|
62 |
+
source="upload",
|
63 |
+
tool="sketch",
|
64 |
+
elem_id="image_upload",
|
65 |
+
type="pil",
|
66 |
+
label="Upload",
|
67 |
+
).style(height=260)
|
68 |
+
|
69 |
+
stable_diffusion_inpaint_prompt = gr.Textbox(
|
70 |
+
lines=1,
|
71 |
+
placeholder="Prompt",
|
72 |
+
show_label=False,
|
73 |
+
)
|
74 |
+
|
75 |
+
stable_diffusion_inpaint_negative_prompt = gr.Textbox(
|
76 |
+
lines=1,
|
77 |
+
placeholder="Negative Prompt",
|
78 |
+
show_label=False,
|
79 |
+
)
|
80 |
+
stable_diffusion_inpaint_model_id = gr.Dropdown(
|
81 |
+
choices=stable_inpiant_model_list,
|
82 |
+
value=stable_inpiant_model_list[0],
|
83 |
+
label="Inpaint Model Id",
|
84 |
+
)
|
85 |
+
with gr.Row():
|
86 |
+
with gr.Column():
|
87 |
+
stable_diffusion_inpaint_guidance_scale = gr.Slider(
|
88 |
+
minimum=0.1,
|
89 |
+
maximum=15,
|
90 |
+
step=0.1,
|
91 |
+
value=7.5,
|
92 |
+
label="Guidance Scale",
|
93 |
+
)
|
94 |
+
|
95 |
+
stable_diffusion_inpaint_num_inference_step = (
|
96 |
+
gr.Slider(
|
97 |
+
minimum=1,
|
98 |
+
maximum=100,
|
99 |
+
step=1,
|
100 |
+
value=50,
|
101 |
+
label="Num Inference Step",
|
102 |
+
)
|
103 |
+
)
|
104 |
+
|
105 |
+
with gr.Row():
|
106 |
+
with gr.Column():
|
107 |
+
stable_diffusion_inpiant_num_images_per_prompt = gr.Slider(
|
108 |
+
minimum=1,
|
109 |
+
maximum=10,
|
110 |
+
step=1,
|
111 |
+
value=1,
|
112 |
+
label="Number Of Images",
|
113 |
+
)
|
114 |
+
stable_diffusion_inpaint_seed_generator = (
|
115 |
+
gr.Slider(
|
116 |
+
minimum=0,
|
117 |
+
maximum=1000000,
|
118 |
+
step=1,
|
119 |
+
value=0,
|
120 |
+
label="Seed(0 for random)",
|
121 |
+
)
|
122 |
+
)
|
123 |
+
|
124 |
+
stable_diffusion_inpaint_predict = gr.Button(
|
125 |
+
value="Generator"
|
126 |
+
)
|
127 |
+
|
128 |
+
with gr.Column():
|
129 |
+
output_image = gr.Gallery(
|
130 |
+
label="Generated images",
|
131 |
+
show_label=False,
|
132 |
+
elem_id="gallery",
|
133 |
+
).style(grid=(1, 2))
|
134 |
+
|
135 |
+
stable_diffusion_inpaint_predict.click(
|
136 |
+
fn=StableDiffusionInpaintGenerator().generate_image,
|
137 |
+
inputs=[
|
138 |
+
stable_diffusion_inpaint_image_file,
|
139 |
+
stable_diffusion_inpaint_model_id,
|
140 |
+
stable_diffusion_inpaint_prompt,
|
141 |
+
stable_diffusion_inpaint_negative_prompt,
|
142 |
+
stable_diffusion_inpiant_num_images_per_prompt,
|
143 |
+
stable_diffusion_inpaint_guidance_scale,
|
144 |
+
stable_diffusion_inpaint_num_inference_step,
|
145 |
+
stable_diffusion_inpaint_seed_generator,
|
146 |
+
],
|
147 |
+
outputs=[output_image],
|
148 |
+
)
|
diffusion_webui/diffusion_models/stable_diffusion/text2img_app.py
ADDED
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
import torch
|
3 |
+
from diffusers import StableDiffusionPipeline
|
4 |
+
|
5 |
+
from diffusion_webui.utils.model_list import stable_model_list
|
6 |
+
from diffusion_webui.utils.scheduler_list import get_scheduler_list
|
7 |
+
|
8 |
+
|
9 |
+
class StableDiffusionText2ImageGenerator:
|
10 |
+
def __init__(self):
|
11 |
+
self.pipe = None
|
12 |
+
|
13 |
+
def load_model(
|
14 |
+
self,
|
15 |
+
model_path,
|
16 |
+
scheduler,
|
17 |
+
):
|
18 |
+
if self.pipe is None:
|
19 |
+
self.pipe = StableDiffusionPipeline.from_pretrained(
|
20 |
+
model_path, safety_checker=None, torch_dtype=torch.float16
|
21 |
+
)
|
22 |
+
|
23 |
+
self.pipe = get_scheduler_list(pipe=self.pipe, scheduler=scheduler)
|
24 |
+
self.pipe.to("cuda")
|
25 |
+
self.pipe.enable_xformers_memory_efficient_attention()
|
26 |
+
|
27 |
+
return self.pipe
|
28 |
+
|
29 |
+
def generate_image(
|
30 |
+
self,
|
31 |
+
model_path: str,
|
32 |
+
prompt: str,
|
33 |
+
negative_prompt: str,
|
34 |
+
num_images_per_prompt: int,
|
35 |
+
scheduler: str,
|
36 |
+
guidance_scale: int,
|
37 |
+
num_inference_step: int,
|
38 |
+
height: int,
|
39 |
+
width: int,
|
40 |
+
seed_generator=0,
|
41 |
+
):
|
42 |
+
pipe = self.load_model(
|
43 |
+
model_path=model_path,
|
44 |
+
scheduler=scheduler,
|
45 |
+
)
|
46 |
+
if seed_generator == 0:
|
47 |
+
random_seed = torch.randint(0, 1000000, (1,))
|
48 |
+
generator = torch.manual_seed(random_seed)
|
49 |
+
else:
|
50 |
+
generator = torch.manual_seed(seed_generator)
|
51 |
+
|
52 |
+
images = pipe(
|
53 |
+
prompt=prompt,
|
54 |
+
height=height,
|
55 |
+
width=width,
|
56 |
+
negative_prompt=negative_prompt,
|
57 |
+
num_images_per_prompt=num_images_per_prompt,
|
58 |
+
num_inference_steps=num_inference_step,
|
59 |
+
guidance_scale=guidance_scale,
|
60 |
+
generator=generator,
|
61 |
+
).images
|
62 |
+
|
63 |
+
return images
|
64 |
+
|
65 |
+
def app():
|
66 |
+
with gr.Blocks():
|
67 |
+
with gr.Row():
|
68 |
+
with gr.Column():
|
69 |
+
text2image_prompt = gr.Textbox(
|
70 |
+
lines=1,
|
71 |
+
placeholder="Prompt",
|
72 |
+
show_label=False,
|
73 |
+
)
|
74 |
+
|
75 |
+
text2image_negative_prompt = gr.Textbox(
|
76 |
+
lines=1,
|
77 |
+
placeholder="Negative Prompt",
|
78 |
+
show_label=False,
|
79 |
+
)
|
80 |
+
with gr.Row():
|
81 |
+
with gr.Column():
|
82 |
+
text2image_model_path = gr.Dropdown(
|
83 |
+
choices=stable_model_list,
|
84 |
+
value=stable_model_list[0],
|
85 |
+
label="Text-Image Model Id",
|
86 |
+
)
|
87 |
+
|
88 |
+
text2image_guidance_scale = gr.Slider(
|
89 |
+
minimum=0.1,
|
90 |
+
maximum=15,
|
91 |
+
step=0.1,
|
92 |
+
value=7.5,
|
93 |
+
label="Guidance Scale",
|
94 |
+
)
|
95 |
+
|
96 |
+
text2image_num_inference_step = gr.Slider(
|
97 |
+
minimum=1,
|
98 |
+
maximum=100,
|
99 |
+
step=1,
|
100 |
+
value=50,
|
101 |
+
label="Num Inference Step",
|
102 |
+
)
|
103 |
+
text2image_num_images_per_prompt = gr.Slider(
|
104 |
+
minimum=1,
|
105 |
+
maximum=30,
|
106 |
+
step=1,
|
107 |
+
value=1,
|
108 |
+
label="Number Of Images",
|
109 |
+
)
|
110 |
+
with gr.Row():
|
111 |
+
with gr.Column():
|
112 |
+
|
113 |
+
text2image_scheduler = gr.Dropdown(
|
114 |
+
choices=[
|
115 |
+
"DDIM",
|
116 |
+
"EulerA",
|
117 |
+
"Euler",
|
118 |
+
"LMS",
|
119 |
+
"Heun",
|
120 |
+
],
|
121 |
+
value="DDIM",
|
122 |
+
label="Scheduler",
|
123 |
+
)
|
124 |
+
|
125 |
+
text2image_height = gr.Slider(
|
126 |
+
minimum=128,
|
127 |
+
maximum=1280,
|
128 |
+
step=32,
|
129 |
+
value=512,
|
130 |
+
label="Image Height",
|
131 |
+
)
|
132 |
+
|
133 |
+
text2image_width = gr.Slider(
|
134 |
+
minimum=128,
|
135 |
+
maximum=1280,
|
136 |
+
step=32,
|
137 |
+
value=512,
|
138 |
+
label="Image Width",
|
139 |
+
)
|
140 |
+
text2image_seed_generator = gr.Slider(
|
141 |
+
label="Seed(0 for random)",
|
142 |
+
minimum=0,
|
143 |
+
maximum=1000000,
|
144 |
+
value=0,
|
145 |
+
)
|
146 |
+
text2image_predict = gr.Button(value="Generator")
|
147 |
+
|
148 |
+
with gr.Column():
|
149 |
+
output_image = gr.Gallery(
|
150 |
+
label="Generated images",
|
151 |
+
show_label=False,
|
152 |
+
elem_id="gallery",
|
153 |
+
).style(grid=(1, 2), height=200)
|
154 |
+
|
155 |
+
text2image_predict.click(
|
156 |
+
fn=StableDiffusionText2ImageGenerator().generate_image,
|
157 |
+
inputs=[
|
158 |
+
text2image_model_path,
|
159 |
+
text2image_prompt,
|
160 |
+
text2image_negative_prompt,
|
161 |
+
text2image_num_images_per_prompt,
|
162 |
+
text2image_scheduler,
|
163 |
+
text2image_guidance_scale,
|
164 |
+
text2image_num_inference_step,
|
165 |
+
text2image_height,
|
166 |
+
text2image_width,
|
167 |
+
text2image_seed_generator,
|
168 |
+
],
|
169 |
+
outputs=output_image,
|
170 |
+
)
|
diffusion_webui/helpers.py
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from diffusion_webui.diffusion_models.controlnet.controlnet_canny import (
|
2 |
+
StableDiffusionControlNetCannyGenerator,
|
3 |
+
)
|
4 |
+
from diffusion_webui.diffusion_models.controlnet.controlnet_depth import (
|
5 |
+
StableDiffusionControlNetDepthGenerator,
|
6 |
+
)
|
7 |
+
from diffusion_webui.diffusion_models.controlnet.controlnet_hed import (
|
8 |
+
StableDiffusionControlNetHEDGenerator,
|
9 |
+
)
|
10 |
+
from diffusion_webui.diffusion_models.controlnet.controlnet_inpaint.controlnet_inpaint_app import (
|
11 |
+
StableDiffusionControlInpaintNetCannyGenerator,
|
12 |
+
)
|
13 |
+
from diffusion_webui.diffusion_models.controlnet.controlnet_mlsd import (
|
14 |
+
StableDiffusionControlNetMLSDGenerator,
|
15 |
+
)
|
16 |
+
from diffusion_webui.diffusion_models.controlnet.controlnet_pose import (
|
17 |
+
StableDiffusionControlNetPoseGenerator,
|
18 |
+
)
|
19 |
+
from diffusion_webui.diffusion_models.controlnet.controlnet_scribble import (
|
20 |
+
StableDiffusionControlNetScribbleGenerator,
|
21 |
+
)
|
22 |
+
from diffusion_webui.diffusion_models.controlnet.controlnet_seg import (
|
23 |
+
StableDiffusionControlNetSegGenerator,
|
24 |
+
)
|
25 |
+
from diffusion_webui.diffusion_models.stable_diffusion.img2img_app import (
|
26 |
+
StableDiffusionImage2ImageGenerator,
|
27 |
+
)
|
28 |
+
from diffusion_webui.diffusion_models.stable_diffusion.inpaint_app import (
|
29 |
+
StableDiffusionInpaintGenerator,
|
30 |
+
)
|
31 |
+
from diffusion_webui.diffusion_models.stable_diffusion.text2img_app import (
|
32 |
+
StableDiffusionText2ImageGenerator,
|
33 |
+
)
|
diffusion_webui/utils/__init__.py
ADDED
File without changes
|
diffusion_webui/utils/model_list.py
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
stable_model_list = [
|
2 |
+
"runwayml/stable-diffusion-v1-5",
|
3 |
+
"stabilityai/stable-diffusion-2-1",
|
4 |
+
]
|
5 |
+
|
6 |
+
controlnet_canny_model_list = [
|
7 |
+
"lllyasviel/sd-controlnet-canny",
|
8 |
+
"thibaud/controlnet-sd21-canny-diffusers",
|
9 |
+
]
|
10 |
+
|
11 |
+
controlnet_depth_model_list = [
|
12 |
+
"lllyasviel/sd-controlnet-depth",
|
13 |
+
"thibaud/controlnet-sd21-depth-diffusers",
|
14 |
+
]
|
15 |
+
|
16 |
+
controlnet_pose_model_list = [
|
17 |
+
"lllyasviel/sd-controlnet-openpose",
|
18 |
+
"thibaud/controlnet-sd21-openpose-diffusers",
|
19 |
+
]
|
20 |
+
|
21 |
+
controlnet_hed_model_list = [
|
22 |
+
"lllyasviel/sd-controlnet-hed",
|
23 |
+
"thibaud/controlnet-sd21-hed-diffusers",
|
24 |
+
]
|
25 |
+
|
26 |
+
controlnet_scribble_model_list = [
|
27 |
+
"lllyasviel/sd-controlnet-scribble",
|
28 |
+
"thibaud/controlnet-sd21-scribble-diffusers",
|
29 |
+
]
|
30 |
+
stable_inpiant_model_list = [
|
31 |
+
"stabilityai/stable-diffusion-2-inpainting",
|
32 |
+
"runwayml/stable-diffusion-inpainting",
|
33 |
+
]
|
diffusion_webui/utils/scheduler_list.py
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from diffusers import (
|
2 |
+
DDIMScheduler,
|
3 |
+
EulerAncestralDiscreteScheduler,
|
4 |
+
EulerDiscreteScheduler,
|
5 |
+
HeunDiscreteScheduler,
|
6 |
+
LMSDiscreteScheduler,
|
7 |
+
UniPCMultistepScheduler,
|
8 |
+
)
|
9 |
+
|
10 |
+
SCHEDULER_LIST = [
|
11 |
+
"DDIM",
|
12 |
+
"EulerA",
|
13 |
+
"Euler",
|
14 |
+
"LMS",
|
15 |
+
"Heun",
|
16 |
+
"UniPC",
|
17 |
+
]
|
18 |
+
|
19 |
+
|
20 |
+
def get_scheduler_list(pipe, scheduler):
|
21 |
+
if scheduler == SCHEDULER_LIST[0]:
|
22 |
+
pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
|
23 |
+
|
24 |
+
elif scheduler == SCHEDULER_LIST[1]:
|
25 |
+
pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(
|
26 |
+
pipe.scheduler.config
|
27 |
+
)
|
28 |
+
|
29 |
+
elif scheduler == SCHEDULER_LIST[2]:
|
30 |
+
pipe.scheduler = EulerDiscreteScheduler.from_config(
|
31 |
+
pipe.scheduler.config
|
32 |
+
)
|
33 |
+
|
34 |
+
elif scheduler == SCHEDULER_LIST[3]:
|
35 |
+
pipe.scheduler = LMSDiscreteScheduler.from_config(pipe.scheduler.config)
|
36 |
+
|
37 |
+
elif scheduler == SCHEDULER_LIST[4]:
|
38 |
+
pipe.scheduler = HeunDiscreteScheduler.from_config(
|
39 |
+
pipe.scheduler.config
|
40 |
+
)
|
41 |
+
|
42 |
+
elif scheduler == SCHEDULER_LIST[5]:
|
43 |
+
pipe.scheduler = UniPCMultistepScheduler.from_config(
|
44 |
+
pipe.scheduler.config
|
45 |
+
)
|
46 |
+
|
47 |
+
return pipe
|