bonk

app.py

@@ -0,0 +1,294 @@
+#!/usr/bin/env python
+
+import os
+import random
+
+import gradio as gr
+import numpy as np
+import PIL.Image
+import torch
+import torchvision.transforms.functional as TF
+from diffusers import (
+    AutoencoderKL,
+    EulerAncestralDiscreteScheduler,
+    StableDiffusionXLAdapterPipeline,
+    T2IAdapter,
+)
+
+from modelscope.pipelines import pipeline
+from modelscope.outputs import OutputKeys
+
+DESCRIPTION = '''# doodle2vid
+Combining T2I-Adapter-SDXL with MS-Image2Video to create a doodle to video pipeline.
+Shout-out to [fffiloni](https://huggingface.co/fffiloni) & [ARC Lab, Tencent PCG](https://huggingface.co/TencentARC) 🗣️
+
+How to use: Draw a doodle in the canvas, and click "Run" to generate a video.
+You can also provide a prompt with more details and choose a style.
+'''
+
+if not torch.cuda.is_available():
+    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
+
+style_list = [
+    {
+        "name": "(No style)",
+        "prompt": "{prompt}",
+        "negative_prompt": "",
+    },
+    {
+        "name": "Cinematic",
+        "prompt": "cinematic still {prompt} . emotional, harmonious, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy",
+        "negative_prompt": "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured",
+    },
+    {
+        "name": "3D Model",
+        "prompt": "professional 3d model {prompt} . octane render, highly detailed, volumetric, dramatic lighting",
+        "negative_prompt": "ugly, deformed, noisy, low poly, blurry, painting",
+    },
+    {
+        "name": "Anime",
+        "prompt": "anime artwork {prompt} . anime style, key visual, vibrant, studio anime,  highly detailed",
+        "negative_prompt": "photo, deformed, black and white, realism, disfigured, low contrast",
+    },
+    {
+        "name": "Digital Art",
+        "prompt": "concept art {prompt} . digital artwork, illustrative, painterly, matte painting, highly detailed",
+        "negative_prompt": "photo, photorealistic, realism, ugly",
+    },
+    {
+        "name": "Photographic",
+        "prompt": "cinematic photo {prompt} . 35mm photograph, film, bokeh, professional, 4k, highly detailed",
+        "negative_prompt": "drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly",
+    },
+    {
+        "name": "Pixel art",
+        "prompt": "pixel-art {prompt} . low-res, blocky, pixel art style, 8-bit graphics",
+        "negative_prompt": "sloppy, messy, blurry, noisy, highly detailed, ultra textured, photo, realistic",
+    },
+    {
+        "name": "Fantasy art",
+        "prompt": "ethereal fantasy concept art of  {prompt} . magnificent, celestial, ethereal, painterly, epic, majestic, magical, fantasy art, cover art, dreamy",
+        "negative_prompt": "photographic, realistic, realism, 35mm film, dslr, cropped, frame, text, deformed, glitch, noise, noisy, off-center, deformed, cross-eyed, closed eyes, bad anatomy, ugly, disfigured, sloppy, duplicate, mutated, black and white",
+    },
+    {
+        "name": "Neonpunk",
+        "prompt": "neonpunk style {prompt} . cyberpunk, vaporwave, neon, vibes, vibrant, stunningly beautiful, crisp, detailed, sleek, ultramodern, magenta highlights, dark purple shadows, high contrast, cinematic, ultra detailed, intricate, professional",
+        "negative_prompt": "painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured",
+    },
+    {
+        "name": "Manga",
+        "prompt": "manga style {prompt} . vibrant, high-energy, detailed, iconic, Japanese comic style",
+        "negative_prompt": "ugly, deformed, noisy, blurry, low contrast, realism, photorealistic, Western comic style",
+    },
+]
+
+styles = {k["name"]: (k["prompt"], k["negative_prompt"]) for k in style_list}
+STYLE_NAMES = list(styles.keys())
+DEFAULT_STYLE_NAME = "(No style)"
+
+
+def apply_style(style_name: str, positive: str, negative: str = "") -> tuple[str, str]:
+    p, n = styles.get(style_name, styles[DEFAULT_STYLE_NAME])
+    return p.replace("{prompt}", positive), n + negative
+
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+if torch.cuda.is_available():
+    model_id = "stabilityai/stable-diffusion-xl-base-1.0"
+    adapter = T2IAdapter.from_pretrained(
+        "TencentARC/t2i-adapter-sketch-sdxl-1.0", torch_dtype=torch.float16, variant="fp16"
+    )
+    scheduler = EulerAncestralDiscreteScheduler.from_pretrained(model_id, subfolder="scheduler")
+    pipe = StableDiffusionXLAdapterPipeline.from_pretrained(
+        model_id,
+        vae=AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16),
+        adapter=adapter,
+        scheduler=scheduler,
+        torch_dtype=torch.float16,
+        variant="fp16",
+    )
+    pipe.to(device)
+else:
+    pipe = None
+
+MAX_SEED = np.iinfo(np.int32).max
+video_pipe = pipeline(task='image-to-video', model='damo/Image-to-Video', model_revision='v1.1.0')
+
+
+def randomize_seed_fn(seed: int, randomize_seed: bool) -> int:
+    if randomize_seed:
+        seed = random.randint(0, MAX_SEED)
+    return seed
+
+def inferVideo(image: PIL.Image.Image) -> str:
+    # Save the passed image to a temp file
+    temp_path = "temp_input_image.png"
+    image.save(temp_path)
+    
+    output_video_path = video_pipe(temp_path, output_video='output.mp4')[OutputKeys.OUTPUT_VIDEO]
+    print(output_video_path)
+    return output_video_path
+
+def inferImage(
+    image: PIL.Image.Image,
+    prompt: str,
+    negative_prompt: str,
+    style_name: str = DEFAULT_STYLE_NAME,
+    num_steps: int = 25,
+    guidance_scale: float = 5,
+    adapter_conditioning_scale: float = 0.8,
+    adapter_conditioning_factor: float = 0.8,
+    seed: int = 0,
+    progress=gr.Progress(track_tqdm=True),
+) -> PIL.Image.Image:
+    image = image.convert("RGB")
+    image = TF.to_tensor(image) > 0.5
+    image = TF.to_pil_image(image.to(torch.float32))
+
+    prompt, negative_prompt = apply_style(style_name, prompt, negative_prompt)
+
+    generator = torch.Generator(device=device).manual_seed(seed)
+    out = pipe(
+        prompt=prompt,
+        negative_prompt=negative_prompt,
+        image=image,
+        num_inference_steps=num_steps,
+        generator=generator,
+        guidance_scale=guidance_scale,
+        adapter_conditioning_scale=adapter_conditioning_scale,
+        adapter_conditioning_factor=adapter_conditioning_factor,
+    ).images[0]
+    
+    return out
+
+
+with gr.Blocks(css="style.css") as demo:
+    gr.Markdown(DESCRIPTION, elem_id="description")
+
+    with gr.Row():
+        with gr.Column():
+            with gr.Group():
+                image = gr.Image(
+                    source="canvas",
+                    tool="sketch",
+                    type="pil",
+                    image_mode="L",
+                    invert_colors=True,
+                    shape=(1024, 1024),
+                    brush_radius=4,
+                    height=440,
+                )
+                prompt = gr.Textbox(label="Prompt")
+                style = gr.Dropdown(label="Style", choices=STYLE_NAMES, value=DEFAULT_STYLE_NAME)
+                run_button = gr.Button("Run")
+            with gr.Accordion("Advanced options", open=False):
+                negative_prompt = gr.Textbox(
+                    label="Negative prompt",
+                    value=" extra digit, fewer digits, cropped, worst quality, low quality, glitch, deformed, mutated, ugly, disfigured",
+                )
+                num_steps = gr.Slider(
+                    label="Number of steps",
+                    minimum=1,
+                    maximum=50,
+                    step=1,
+                    value=25,
+                )
+                guidance_scale = gr.Slider(
+                    label="Guidance scale",
+                    minimum=0.1,
+                    maximum=10.0,
+                    step=0.1,
+                    value=5,
+                )
+                adapter_conditioning_scale = gr.Slider(
+                    label="Adapter conditioning scale",
+                    minimum=0.5,
+                    maximum=1,
+                    step=0.1,
+                    value=0.8,
+                )
+                adapter_conditioning_factor = gr.Slider(
+                    label="Adapter conditioning factor",
+                    info="Fraction of timesteps for which adapter should be applied",
+                    minimum=0.5,
+                    maximum=1,
+                    step=0.1,
+                    value=0.8,
+                )
+                seed = gr.Slider(
+                    label="Seed",
+                    minimum=0,
+                    maximum=MAX_SEED,
+                    step=1,
+                    value=0,
+                )
+                randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+        with gr.Column():
+            result_image = gr.Image(label="Intermediate Image Output", height=400)
+            result_video = gr.Video(label="Final Video Output", height=400)
+
+    inputs = [
+        image,
+        prompt,
+        negative_prompt,
+        style,
+        num_steps,
+        guidance_scale,
+        adapter_conditioning_scale,
+        adapter_conditioning_factor,
+        seed,
+    ]
+    prompt.submit(
+        fn=randomize_seed_fn,
+        inputs=[seed, randomize_seed],
+        outputs=seed,
+        queue=False,
+        api_name=False,
+    ).then(
+        fn=inferImage,
+        inputs=inputs,
+        outputs=result_image,
+        api_name=False,
+    ).then(
+        fn=inferVideo,
+        inputs=result_image,
+        outputs=result_video,
+        api_name=False,
+    )
+    negative_prompt.submit(
+        fn=randomize_seed_fn,
+        inputs=[seed, randomize_seed],
+        outputs=seed,
+        queue=False,
+        api_name=False,
+    ).then(
+        fn=inferImage,
+        inputs=inputs,
+        outputs=result_image,
+        api_name=False,
+    ).then(
+        fn=inferVideo,
+        inputs=result_image,
+        outputs=result_video,
+        api_name=False,
+    )
+    run_button.click(
+        fn=randomize_seed_fn,
+        inputs=[seed, randomize_seed],
+        outputs=seed,
+        queue=False,
+        api_name=False,
+    ).then(
+        fn=inferImage,
+        inputs=inputs,
+        outputs=result_image,
+        api_name=False,
+    ).then(
+        fn=inferVideo,
+        inputs=result_image,
+        outputs=result_video,
+        api_name=False,
+    )
+
+if __name__ == "__main__":
+    demo.queue(max_size=20).launch()

requirements.txt

@@ -0,0 +1,21 @@
+accelerate==0.22.0
+git+https://github.com/huggingface/diffusers@t2i-adapter-load-lora
+gradio==3.43.1
+Pillow==10.0.0
+safetensors==0.3.3
+torch==2.0.1
+torchvision==0.15.2
+transformers==4.33.1
+xformers==0.0.20
+modelscope==1.8.4
+open_clip_torch>=2.0.2
+opencv-python-headless
+opencv-python
+einops>=0.4
+rotary-embedding-torch
+fairscale
+scipy
+imageio
+pytorch-lightning
+torchsde
+easydict