OriLib's picture
Create app.py
f3f94c7 verified
raw
history blame
3.8 kB
import spaces
import cv2
import gradio as gr
import torch
from diffusers import (
AutoencoderKL,
EulerAncestralDiscreteScheduler,
)
from diffusers.utils import load_image
from replace_bg.model.pipeline_controlnet_sd_xl import StableDiffusionXLControlNetPipeline
from replace_bg.model.controlnet import ControlNetModel
from replace_bg.utilities import resize_image, remove_bg_from_image, paste_fg_over_image, get_control_image_tensor
controlnet = ControlNetModel.from_pretrained("briaai/BRIA-2.3-ControlNet-BG-Gen", torch_dtype=torch.float16)
vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
pipe = StableDiffusionXLControlNetPipeline.from_pretrained("briaai/BRIA-2.3", controlnet=controlnet, torch_dtype=torch.float16, vae=vae).to('cuda:0')
pipe.scheduler = EulerAncestralDiscreteScheduler(
beta_start=0.00085,
beta_end=0.012,
beta_schedule="scaled_linear",
num_train_timesteps=1000,
steps_offset=1
)
@spaces.GPU
def generate_(prompt, negative_prompt, control_tensor, num_steps, controlnet_conditioning_scale, seed):
generator = torch.Generator("cuda").manual_seed(seed)
gen_img = pipe(
negative_prompt=negative_prompt,
prompt=prompt,
controlnet_conditioning_scale=controlnet_conditioning_scale,
num_inference_steps=num_steps,
image = control_tensor,
generator=generator
).images[0]
result_image = paste_fg_over_image(gen_img, image, mask)
return result_image
@spaces.GPU
def process(input_image, prompt, negative_prompt, num_steps, controlnet_conditioning_scale, seed):
# resize input_image to 1024x1024
input_image = resize_image(input_image)
image = resize_image(image)
mask = remove_bg_from_image(image_path)
control_tensor = get_control_image_tensor(pipe.vae, image, mask)
images = generate_(prompt, negative_prompt, control_tensor, num_steps, controlnet_conditioning_scale, seed)
return [depth_image, images[0]]
block = gr.Blocks().queue()
with block:
gr.Markdown("## BRIA Generate Background")
gr.HTML('''
<p style="margin-bottom: 10px; font-size: 94%">
This is a demo for ControlNet Depth that using
<a href="briaai/BRIA-2.3-ControlNet-BG-Gen" target="_blank">BRIA 2.3 text-to-image model</a> as backbone.
Trained on licensed data, BRIA 2.3 provide full legal liability coverage for copyright and privacy infringement.
</p>
''')
with gr.Row():
with gr.Column():
input_image = gr.Image(sources=None, type="pil") # None for upload, ctrl+v and webcam
prompt = gr.Textbox(label="Prompt")
negative_prompt = gr.Textbox(label="Negative prompt", value="Logo,Watermark,Text,Ugly,Morbid,Extra fingers,Poorly drawn hands,Mutation,Blurry,Extra limbs,Gross proportions,Missing arms,Mutated hands,Long neck,Duplicate,Mutilated,Mutilated hands,Poorly drawn face,Deformed,Bad anatomy,Cloned face,Malformed limbs,Missing legs,Too many fingers")
num_steps = gr.Slider(label="Number of steps", minimum=25, maximum=100, value=50, step=1)
controlnet_conditioning_scale = gr.Slider(label="ControlNet conditioning scale", minimum=0.1, maximum=2.0, value=1.0, step=0.05)
seed = gr.Slider(label="Seed", minimum=0, maximum=2147483647, step=1, randomize=True,)
run_button = gr.Button(value="Run")
with gr.Column():
result_gallery = gr.Gallery(label='Output', show_label=False, elem_id="gallery", columns=[2], height='auto')
ips = [input_image, prompt, negative_prompt, num_steps, controlnet_conditioning_scale, seed]
run_button.click(fn=process, inputs=ips, outputs=[result_gallery])
block.launch(debug = True)