Delete app.py

app.py

@@ -1,213 +0,0 @@
-import os
-import gradio as gr
-import torch
-import spaces
-
-from PIL import Image
-from huggingface_hub import hf_hub_download
-from safetensors.torch import load_file
-
-from diffusers import ControlNetModel
-from transformers import CLIPTextModel, CLIPTokenizer
-from diffusers.models.autoencoders.autoencoder_kl import AutoencoderKL
-from diffusers.models.unets.unet_2d_condition import UNet2DConditionModel
-
-# Local files you must upload to the Space (same folder as this app.py)
-from pipeline import build_controlnet_pipe
-from prepare_laion import CannyCFG, canny_auto_median_bilateral
-
-# -----------------------------
-# Config
-# -----------------------------
-BASE_MODEL = "sd-legacy/stable-diffusion-v1-5"
-WEIGHTS_REPO= "mvp-lab/ControlNet_Weight"
-WEIGHTS_FILENAME = "diffusion_pytorch_model_1.safetensors"
-
-# Download (cached) and get the local path
-CONTROLNET_PATH = hf_hub_download(
-    repo_id=WEIGHTS_REPO,
-    filename=WEIGHTS_FILENAME,
-    repo_type="model"
-)
-
-# For ZeroGPU, keep dtype float32 for safety/compatibility.
-DTYPE = torch.float32
-DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-
-vae = AutoencoderKL.from_pretrained(BASE_MODEL, subfolder="vae", torch_dtype=DTYPE)
-unet = UNet2DConditionModel.from_pretrained(BASE_MODEL, subfolder="unet", torch_dtype=DTYPE)
-tokenizer = CLIPTokenizer.from_pretrained(BASE_MODEL, subfolder="tokenizer")
-text_encoder = CLIPTextModel.from_pretrained(BASE_MODEL, subfolder="text_encoder", torch_dtype=DTYPE)
-
-vae.requires_grad_(False)
-unet.requires_grad_(False)
-text_encoder.requires_grad_(False)
-
-controlnet = ControlNetModel.from_unet(unet, conditioning_channels=3)
-state = load_file(CONTROLNET_PATH)
-missing, unexpected = controlnet.load_state_dict(state, strict=False)
-print(f"[ControlNet] missing={len(missing)}, unexpected={len(unexpected)}")
-
-pipe = build_controlnet_pipe(
-        base_model_name=BASE_MODEL,
-        controlnet=controlnet,
-        vae=vae,
-        unet=unet,
-        text_encoder=text_encoder,
-        tokenizer=tokenizer,
-        device=DEVICE,
-        weight_dtype=DTYPE,
-        use_unipc=True,
-)
-
-@torch.inference_mode()
-def run_pipeline(
-    input_image: Image.Image,
-    prompt: str,
-    negative_prompt: str = "",
-    guidance_scale: float = 7.5,
-    num_inference_steps: int = 50,
-    num_images: int = 1,
-    controlnet_conditioning_scale: float = 1.0,
-    resolution: int = 512,
-    return_canny: bool = False,
-):
-    if input_image is None:
-        raise ValueError("input_image is None")
-    if num_images < 1:
-        raise ValueError("num_images must be >= 1")
-
-    # Resize input
-    img_rgb = input_image.convert("RGB").resize((resolution, resolution))
-
-    # Compute Canny conditioning image (RGB)
-    canny_cfg = CannyCFG(sigma=0.33, d=7, sigma_color=50, sigma_space=50)
-    canny = canny_auto_median_bilateral(img_rgb, canny_cfg).convert("RGB")
-
-    generators = [torch.Generator(device=DEVICE).manual_seed(i) for i in range(num_images)]
-
-    images = pipe(
-        prompt=[prompt] * num_images,
-        negative_prompt=[negative_prompt] * num_images,
-        image=[canny] * num_images,
-        num_inference_steps=int(num_inference_steps),
-        guidance_scale=float(guidance_scale),
-        height=int(resolution),
-        width=int(resolution),
-        generator=generators,
-        controlnet_conditioning_scale=float(controlnet_conditioning_scale),
-    ).images
-
-    if return_canny:
-        return images, canny
-    return images
-
-@spaces.GPU
-def generate_image(
-    input_image,
-    positive_prompt,
-    negative_prompt,
-    guidance_scale,
-    num_inference_steps,
-    num_images,
-    controlnet_conditioning_scale,
-    resolution,
-):
-
-    if input_image is None:
-        raise gr.Error("Please upload an input image.")
-
-    # If Gradio passes numpy, convert defensively (even though type="pil" should give PIL)
-    if not isinstance(input_image, Image.Image):
-        input_image = Image.fromarray(input_image)
-
-    imgs, canny = run_pipeline(
-        input_image=input_image,
-        prompt=positive_prompt,
-        negative_prompt=negative_prompt,
-        guidance_scale=float(guidance_scale),
-        num_inference_steps=int(num_inference_steps),
-        num_images=int(num_images),
-        controlnet_conditioning_scale=float(controlnet_conditioning_scale),
-        resolution=int(resolution),
-        return_canny=True,
-    )
-    return canny, imgs
-
-# ----------- demo -----------
-with gr.Blocks() as demo:
-    gr.Markdown("## ControlNet (Canny) Demo")
-    gr.Markdown("Upload an image and write prompt(s). The model generates images conditioned on Canny edges.")
-
-    with gr.Row():
-        with gr.Column():
-            input_image = gr.Image(
-                label="Input Image",
-                type="pil",
-                image_mode="RGB",
-            )
-
-            positive_prompt = gr.Textbox(
-                label="Positive Prompt",
-                value="",
-                lines=2,
-                placeholder="Brief description of image",
-            )
-
-            negative_prompt = gr.Textbox(
-                label="Negative Prompt",
-                value="",
-                lines=2,
-                placeholder="e.g., an blurry image with deformed structure",
-            )
-
-            with gr.Row():
-                guidance_scale = gr.Slider(
-                    label="Guidance Scale",
-                    minimum=1.0, maximum=15.0, value=7.5, step=0.1
-                )
-                num_inference_steps = gr.Slider(
-                    label="Steps",
-                    minimum=10, maximum=80, value=50, step=1
-                )
-
-            with gr.Row():
-                num_images = gr.Slider(
-                    label="Number of Images",
-                    minimum=1, maximum=6, value=1, step=1
-                )
-                controlnet_conditioning_scale = gr.Slider(
-                    label="ControlNet Conditioning Scale",
-                    minimum=0.0, maximum=2.0, value=1.0, step=0.05
-                )
-
-            resolution = gr.Dropdown(
-                label="Resolution",
-                choices=[256, 384, 512, 640, 768, 1024],
-                value=512,
-            )
-
-            run_btn = gr.Button("Generate", variant="primary")
-
-        with gr.Column(scale=1):
-            canny_preview = gr.Image(label="Canny edges image", type="pil")
-            gallery = gr.Gallery(label="Generated Images", columns=2, rows=2, height=420)
-
-    run_btn.click(
-        fn=generate_image,
-        inputs=[
-            input_image,
-            positive_prompt,
-            negative_prompt,
-            guidance_scale,
-            num_inference_steps,
-            num_images,
-            controlnet_conditioning_scale,
-            resolution,
-        ],
-        outputs=[canny_preview, gallery],
-    )
-
-
-if __name__ == "__main__":
-    demo.launch()