Update app.py

app.py

@@ -4,47 +4,23 @@ import gradio as gr
 import numpy as np
 from PIL import Image
 from einops import rearrange
-import requests
-import spaces
-from huggingface_hub import login
+from diffusers import FluxControlNetPipeline, FluxControlNetModel
+from diffusers.utils import load_image
 from gradio_imageslider import ImageSlider  # Import ImageSlider
 
-from image_datasets.canny_dataset import canny_processor, c_crop
-from src.flux.sampling import denoise_controlnet, get_noise, get_schedule, prepare, unpack
-from src.flux.util import load_ae, load_clip, load_t5, load_flow_model, load_controlnet, load_safetensors
+# Load the new ControlNet model
+base_model = 'black-forest-labs/FLUX.1-dev'
+controlnet_model = 'InstantX/FLUX.1-dev-Controlnet-Union'
 
-# Download and load the ControlNet model
-model_url = "https://huggingface.co/XLabs-AI/flux-controlnet-canny-v3/resolve/main/flux-canny-controlnet-v3.safetensors?download=true"
-model_path = "./flux-canny-controlnet-v3.safetensors"
-if not os.path.exists(model_path):
-    response = requests.get(model_url)
-    with open(model_path, 'wb') as f:
-        f.write(response.content)
-
-# Source: https://github.com/XLabs-AI/x-flux.git
-name = "flux-dev"
 device = torch.device("cuda")
-offload = False
-is_schnell = name == "flux-schnell"
-
-model, ae, t5, clip, controlnet = None, None, None, None, None
-
-def load_models():
-    global model, ae, t5, clip, controlnet
-    t5 = load_t5(device, max_length=256 if is_schnell else 512)
-    clip = load_clip(device)
-    model = load_flow_model(name, device=device)
-    ae = load_ae(name, device=device)
-    controlnet = load_controlnet(name, device).to(device).to(torch.bfloat16)
 
-    checkpoint = load_safetensors(model_path)
-    controlnet.load_state_dict(checkpoint, strict=False)
-
-load_models()
+controlnet = FluxControlNetModel.from_pretrained(controlnet_model, torch_dtype=torch.bfloat16)
+pipe = FluxControlNetPipeline.from_pretrained(base_model, controlnet=controlnet, torch_dtype=torch.bfloat16)
+pipe.to(device)
 
 def preprocess_image(image, target_width, target_height, crop=True):
     if crop:
-        image = c_crop(image)  # Crop the image to square
+        image = image.crop((0, 0, min(image.size), min(image.size)))  # Crop the image to square
         original_width, original_height = image.size
 
         # Resize to match the target size without stretching
@@ -65,61 +41,50 @@ def preprocess_image(image, target_width, target_height, crop=True):
 
 def preprocess_canny_image(image, target_width, target_height, crop=True):
     image = preprocess_image(image, target_width, target_height, crop=crop)
-    image = canny_processor(image)
+    image = np.array(image.convert('L'))  # Convert to grayscale for Canny processing
+    image = cv2.Canny(image, 100, 200)  # Apply Canny edge detection
+    image = Image.fromarray(image)
     return image
 
-@spaces.GPU(duration=120)
-def generate_image(prompt, control_image, num_steps=50, guidance=4, width=512, height=512, seed=42, random_seed=False):
+def generate_image(prompt, control_image, num_steps=24, guidance=3.5, width=512, height=512, seed=42, random_seed=False, control_mode=0):
     if random_seed:
         seed = np.random.randint(0, 10000)
     
     if not os.path.isdir("./controlnet_results/"):
         os.makedirs("./controlnet_results/")
 
-    torch_device = torch.device("cuda")
-    
-    model.to(torch_device)
-    t5.to(torch_device)
-    clip.to(torch_device)
-    ae.to(torch_device)
-    controlnet.to(torch_device)
-
-    width = 16 * width // 16
-    height = 16 * height // 16
-    timesteps = get_schedule(num_steps, (width // 8) * (height // 8) // (16 * 16), shift=(not is_schnell))
-    
-    processed_input = preprocess_image(control_image, width, height)
-    canny_processed = preprocess_canny_image(control_image, width, height)
-    controlnet_cond = torch.from_numpy((np.array(canny_processed) / 127.5) - 1)
-    controlnet_cond = controlnet_cond.permute(2, 0, 1).unsqueeze(0).to(torch.bfloat16).to(torch_device)
-
     torch.manual_seed(seed)
-    with torch.no_grad():
-        x = get_noise(1, height, width, device=torch_device, dtype=torch.bfloat16, seed=seed)
-        inp_cond = prepare(t5=t5, clip=clip, img=x, prompt=prompt)
 
-        x = denoise_controlnet(model, **inp_cond, controlnet=controlnet, timesteps=timesteps, guidance=guidance, controlnet_cond=controlnet_cond)
-        
-        x = unpack(x.float(), height, width)
-        x = ae.decode(x)
-
-    x1 = x.clamp(-1, 1)
-    x1 = rearrange(x1[-1], "c h w -> h w c")
-    output_img = Image.fromarray((127.5 * (x1 + 1.0)).cpu().byte().numpy())
+    control_image = preprocess_canny_image(control_image, width, height)  # Preprocess the control image for Canny mode
+    
+    controlnet_conditioning_scale = 0.5  # ControlNet conditioning scale
     
-    return [processed_input, output_img]  # Return both images for slider
+    # Generate the image using the pipeline
+    image = pipe(
+        prompt, 
+        control_image=control_image,
+        control_mode=control_mode,
+        width=width,
+        height=height,
+        controlnet_conditioning_scale=controlnet_conditioning_scale,
+        num_inference_steps=num_steps, 
+        guidance_scale=guidance,
+    ).images[0]
+
+    return [control_image, image]  # Return both images for slider
 
 interface = gr.Interface(
     fn=generate_image,
     inputs=[
         gr.Textbox(label="Prompt"),
         gr.Image(type="pil", label="Control Image"),
-        gr.Slider(step=1, minimum=1, maximum=64, value=28, label="Num Steps"),
-        gr.Slider(minimum=0.1, maximum=10, value=4, label="Guidance"),
+        gr.Slider(step=1, minimum=1, maximum=64, value=24, label="Num Steps"),
+        gr.Slider(minimum=0.1, maximum=10, value=3.5, label="Guidance"),
         gr.Slider(minimum=128, maximum=2048, step=128, value=1024, label="Width"),
         gr.Slider(minimum=128, maximum=2048, step=128, value=1024, label="Height"),
         gr.Number(value=42, label="Seed"),
-        gr.Checkbox(label="Random Seed")
+        gr.Checkbox(label="Random Seed"),
+        gr.Radio(choices=[0, 1, 2, 3, 4, 5, 6], value=0, label="Control Mode")
     ],
     outputs=ImageSlider(label="Before / After"),  # Use ImageSlider as the output
     title="FLUX.1 Controlnet Canny",
@@ -128,4 +93,3 @@ interface = gr.Interface(
 
 if __name__ == "__main__":
     interface.launch()
-