Spaces:
Running
on
Zero
Running
on
Zero
| import spaces | |
| import random | |
| import numpy as np | |
| from PIL import Image | |
| import torch | |
| import torchvision.transforms.functional as F | |
| from diffusers import ControlNetModel, StableDiffusionControlNetPipeline, AutoencoderTiny, AutoencoderKL | |
| import gradio as gr | |
| device = "cuda" | |
| weight_type = torch.float16 | |
| controlnet = ControlNetModel.from_pretrained( | |
| "IDKiro/sdxs-512-dreamshaper-sketch", torch_dtype=weight_type | |
| ).to(device) | |
| pipe = StableDiffusionControlNetPipeline.from_pretrained( | |
| "IDKiro/sdxs-512-dreamshaper", controlnet=controlnet, torch_dtype=weight_type | |
| ) | |
| pipe.to(device) | |
| vae_tiny = AutoencoderTiny.from_pretrained( | |
| "IDKiro/sdxs-512-dreamshaper", subfolder="vae" | |
| ) | |
| vae_tiny.to(device, dtype=weight_type) | |
| vae_large = AutoencoderKL.from_pretrained( | |
| "IDKiro/sdxs-512-dreamshaper", subfolder="vae_large" | |
| ) | |
| vae_tiny.to(device, dtype=weight_type) | |
| style_list = [ | |
| { | |
| "name": "No Style", | |
| "prompt": "{prompt}", | |
| }, | |
| { | |
| "name": "Cinematic", | |
| "prompt": "cinematic still {prompt} . emotional, harmonious, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy", | |
| }, | |
| { | |
| "name": "3D Model", | |
| "prompt": "professional 3d model {prompt} . octane render, highly detailed, volumetric, dramatic lighting", | |
| }, | |
| { | |
| "name": "Anime", | |
| "prompt": "anime artwork {prompt} . anime style, key visual, vibrant, studio anime, highly detailed", | |
| }, | |
| { | |
| "name": "Digital Art", | |
| "prompt": "concept art {prompt} . digital artwork, illustrative, painterly, matte painting, highly detailed", | |
| }, | |
| { | |
| "name": "Photographic", | |
| "prompt": "cinematic photo {prompt} . 35mm photograph, film, bokeh, professional, 4k, highly detailed", | |
| }, | |
| { | |
| "name": "Pixel art", | |
| "prompt": "pixel-art {prompt} . low-res, blocky, pixel art style, 8-bit graphics", | |
| }, | |
| { | |
| "name": "Fantasy art", | |
| "prompt": "ethereal fantasy concept art of {prompt} . magnificent, celestial, ethereal, painterly, epic, majestic, magical, fantasy art, cover art, dreamy", | |
| }, | |
| { | |
| "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", | |
| }, | |
| { | |
| "name": "Manga", | |
| "prompt": "manga style {prompt} . vibrant, high-energy, detailed, iconic, Japanese comic style", | |
| }, | |
| ] | |
| styles = {k["name"]: k["prompt"] for k in style_list} | |
| STYLE_NAMES = list(styles.keys()) | |
| DEFAULT_STYLE_NAME = "No Style" | |
| MAX_SEED = np.iinfo(np.int32).max | |
| def randomize_seed_fn(seed: int, randomize_seed: bool) -> int: | |
| if randomize_seed: | |
| seed = random.randint(0, MAX_SEED) | |
| return seed | |
| def run( | |
| image, | |
| prompt, | |
| prompt_template, | |
| style_name, | |
| controlnet_conditioning_scale, | |
| vae_type="tiny vae", | |
| device_type="GPU", | |
| param_dtype="torch.float16", | |
| ): | |
| if vae_type == "tiny vae": | |
| pipe.vae = vae_tiny | |
| elif vae_type == "large vae": | |
| pipe.vae = vae_large | |
| if device_type == "CPU": | |
| device = "cpu" | |
| param_dtype = "torch.float32" | |
| else: | |
| device = "cuda" | |
| pipe.to( | |
| torch_device=device, | |
| torch_dtype=torch.float16 if param_dtype == "torch.float16" else torch.float32, | |
| ) | |
| print(f"prompt: {prompt}") | |
| print("sketch updated") | |
| if image is None: | |
| ones = Image.new("L", (512, 512), 255) | |
| return ones | |
| prompt = prompt_template.replace("{prompt}", prompt) | |
| control_image = Image.fromarray(255 - np.array(image["composite"])[:, :, -1]) | |
| output_pil = pipe( | |
| prompt=prompt, | |
| image=control_image, | |
| width=512, | |
| height=512, | |
| guidance_scale=0.0, | |
| num_inference_steps=1, | |
| num_images_per_prompt=1, | |
| output_type="pil", | |
| controlnet_conditioning_scale=float(controlnet_conditioning_scale), | |
| ).images[0] | |
| return output_pil | |
| with gr.Blocks(theme="monochrome") as demo: | |
| gr.Markdown("# SDXS-512-DreamShaper-Sketch") | |
| gr.Markdown( | |
| "[SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions](https://arxiv.org/abs/2403.16627) | [GitHub](https://github.com/IDKiro/sdxs)" | |
| ) | |
| with gr.Row(): | |
| with gr.Column(): | |
| gr.Markdown("## INPUT") | |
| image = gr.Sketchpad( | |
| type="pil", | |
| image_mode="RGBA", | |
| brush=gr.Brush(colors=["#000000"], color_mode="fixed", default_size=8), | |
| crop_size="1:1", | |
| ) | |
| prompt = gr.Textbox(label="Prompt", value="", show_label=True) | |
| with gr.Row(): | |
| style = gr.Dropdown( | |
| label="Style", | |
| choices=STYLE_NAMES, | |
| value=DEFAULT_STYLE_NAME, | |
| scale=1, | |
| ) | |
| prompt_temp = gr.Textbox( | |
| label="Prompt Style Template", | |
| value=styles[DEFAULT_STYLE_NAME], | |
| scale=2, | |
| max_lines=1, | |
| ) | |
| controlnet_conditioning_scale = gr.Slider( | |
| label="Control Strength", minimum=0, maximum=1, step=0.01, value=0.8 | |
| ) | |
| vae_choices = ["tiny vae", "large vae"] | |
| vae_type = gr.Radio( | |
| vae_choices, | |
| label="Image Decoder Type", | |
| value=vae_choices[0], | |
| interactive=True, | |
| info="To save GPU memory, use tiny vae. For better quality, use large vae.", | |
| ) | |
| device_choices = ["GPU", "CPU"] | |
| device_type = gr.Radio( | |
| device_choices, | |
| label="Device", | |
| value=device_choices[0], | |
| interactive=True, | |
| info="Many thanks to the community for the GPU!", | |
| ) | |
| dtype_choices = ["torch.float16", "torch.float32"] | |
| param_dtype = gr.Radio( | |
| dtype_choices, | |
| label="torch.weight_type", | |
| value=dtype_choices[0], | |
| interactive=True, | |
| info="To save GPU memory, use torch.float16. For better quality, use torch.float32.", | |
| ) | |
| with gr.Column(): | |
| gr.Markdown("## OUTPUT") | |
| result = gr.Image( | |
| label="Result", | |
| show_label=False, | |
| show_download_button=True, | |
| ) | |
| run_button = gr.Button("Run") | |
| gr.Markdown("### Instructions") | |
| gr.Markdown("**1**. Enter a text prompt (e.g. cat)") | |
| gr.Markdown("**2**. Start sketching") | |
| gr.Markdown("**3**. Change the image style using a style template") | |
| gr.Markdown("**4**. Adjust the effect of sketch guidance using the slider") | |
| inputs = [ | |
| image, | |
| prompt, | |
| prompt_temp, | |
| style, | |
| controlnet_conditioning_scale, | |
| vae_type, | |
| device_type, | |
| param_dtype, | |
| ] | |
| outputs = [result] | |
| prompt.submit(fn=run, inputs=inputs, outputs=outputs) | |
| style.change(lambda x: styles[x], inputs=[style], outputs=[prompt_temp]).then( | |
| fn=run, | |
| inputs=inputs, | |
| outputs=outputs, | |
| ) | |
| image.change( | |
| run, | |
| inputs=inputs, | |
| outputs=outputs, | |
| ) | |
| run_button.click( | |
| run, | |
| inputs=inputs, | |
| outputs=outputs, | |
| ) | |
| if __name__ == "__main__": | |
| demo.queue().launch() | |