Create app.py

app.py

@@ -0,0 +1,117 @@
+import spaces
+from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline, AutoencoderKL, EulerAncestralDiscreteScheduler
+from diffusers.utils import load_image
+from PIL import Image
+import torch
+import numpy as np
+import cv2
+import gradio as gr
+from torchvision import transforms 
+
+controlnet = ControlNetModel.from_pretrained(
+    "geyongtao/HumanWild",
+    torch_dtype=torch.float16
+).to('cuda')
+
+pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-xl-base-1.0",
+    controlnet=controlnet,
+    torch_dtype=torch.float16,
+    device_map='auto',
+    low_cpu_mem_usage=True,
+    offload_state_dict=True,
+).to('cuda')
+
+pipe.scheduler = EulerAncestralDiscreteScheduler(
+    beta_start=0.00085,
+    beta_end=0.012,
+    beta_schedule="scaled_linear",
+    num_train_timesteps=1000,
+    steps_offset=1
+)
+# pipe.enable_freeu(b1=1.1, b2=1.1, s1=0.5, s2=0.7)
+# pipe.enable_xformers_memory_efficient_attention()
+pipe.force_zeros_for_empty_prompt = False
+
+# from transformers import DPTFeatureExtractor, DPTForDepthEstimation
+# depth_estimator = DPTForDepthEstimation.from_pretrained("Intel/dpt-hybrid-midas").to("cuda")
+# feature_extractor = DPTFeatureExtractor.from_pretrained("Intel/dpt-hybrid-midas")
+
+def resize_image(image):
+    image = image.convert('RGB')
+    current_size = image.size
+    if current_size[0] > current_size[1]:
+        center_cropped_image = transforms.functional.center_crop(image, (current_size[1], current_size[1]))
+    else:
+        center_cropped_image = transforms.functional.center_crop(image, (current_size[0], current_size[0]))
+    resized_image = transforms.functional.resize(center_cropped_image, (1024, 1024))
+    return resized_image
+
+def get_normal_map(image):
+    image = feature_extractor(images=image, return_tensors="pt").pixel_values.to("cuda")
+    with torch.no_grad(), torch.autocast("cuda"):
+        depth_map = depth_estimator(image).predicted_depth
+    image = transforms.functional.center_crop(image, min(image.shape[-2:]))
+    depth_map = torch.nn.functional.interpolate(
+        depth_map.unsqueeze(1),
+        size=(1024, 1024),
+        mode="bicubic",
+        align_corners=False,
+    )
+    depth_min = torch.amin(depth_map, dim=[1, 2, 3], keepdim=True)
+    depth_max = torch.amax(depth_map, dim=[1, 2, 3], keepdim=True)
+    depth_map = (depth_map - depth_min) / (depth_max - depth_min)
+    image = torch.cat([depth_map] * 3, dim=1)
+    image = image.permute(0, 2, 3, 1).cpu().numpy()[0]
+    image = Image.fromarray((image * 255.0).clip(0, 255).astype(np.uint8))
+    return image
+
+
+@spaces.GPU
+def generate_(prompt, negative_prompt, canny_image, num_steps, controlnet_conditioning_scale, seed):
+    generator = torch.Generator("cuda").manual_seed(seed)    
+    images = pipe(
+    prompt, negative_prompt=negative_prompt, image=canny_image, num_inference_steps=num_steps, controlnet_conditioning_scale=float(controlnet_conditioning_scale),
+    generator=generator,
+    ).images
+    return images
+
+@spaces.GPU
+def process(normal_image, prompt, negative_prompt, num_steps, controlnet_conditioning_scale, seed):
+    # resize input_image to 1024x1024
+    normal_image = resize_image(normal_image)
+    # depth_image = get_depth_map(input_image)
+    images = generate_(prompt, negative_prompt, normal_image, num_steps, controlnet_conditioning_scale, seed)
+
+    return [depth_image, images[0]]
+
+
+
+block = gr.Blocks().queue()
+
+with block:
+    gr.Markdown("## BRIA 2.2 ControlNet Depth")
+    gr.HTML('''
+      <p style="margin-bottom: 10px; font-size: 94%">
+        This is a demo for ControlNet Surface Normal that using
+        <a href="https://huggingface.co/geyongtao/HumanWild" target="_blank"> HumanWild model</a> as backbone. 
+      </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)