Spaces:
Runtime error
Runtime error
| from diffusers import StableDiffusionControlNetPipeline, ControlNetModel | |
| from diffusers import UniPCMultistepScheduler | |
| import gradio as gr | |
| import numpy as np | |
| import torch | |
| import base64 | |
| import cv2 | |
| from io import BytesIO | |
| from PIL import Image, ImageFilter | |
| from share_btn import community_icon_html, loading_icon_html, share_js, share_btn_css | |
| # Constants | |
| low_threshold = 100 | |
| high_threshold = 200 | |
| canvas_html = '<pose-maker/>' | |
| load_js = """ | |
| async () => { | |
| const url = "https://huggingface.co./datasets/mishig/gradio-components/raw/main/mannequinAll.js" | |
| fetch(url) | |
| .then(res => res.text()) | |
| .then(text => { | |
| const script = document.createElement('script'); | |
| script.type = "module" | |
| script.src = URL.createObjectURL(new Blob([text], { type: 'application/javascript' })); | |
| document.head.appendChild(script); | |
| }); | |
| } | |
| """ | |
| get_js_image = """ | |
| async (canvas, prompt) => { | |
| const poseMakerEl = document.querySelector("pose-maker"); | |
| const imgBase64 = poseMakerEl.captureScreenshotDepthMap(); | |
| return [imgBase64, prompt] | |
| } | |
| """ | |
| # Models | |
| controlnet = ControlNetModel.from_pretrained( | |
| "lllyasviel/control_v11p_sd15_canny", torch_dtype=torch.float16 | |
| ) | |
| pipe = StableDiffusionControlNetPipeline.from_pretrained( | |
| "runwayml/stable-diffusion-v1-5", controlnet=controlnet, safety_checker=None, torch_dtype=torch.float16 | |
| ) | |
| pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config) | |
| # This command loads the individual model components on GPU on-demand. So, we don't | |
| # need to explicitly call pipe.to("cuda"). | |
| pipe.enable_model_cpu_offload() | |
| # xformers | |
| pipe.enable_xformers_memory_efficient_attention() | |
| # Generator seed, | |
| generator = torch.manual_seed(0) | |
| def get_canny_filter(image): | |
| if not isinstance(image, np.ndarray): | |
| image = np.array(image) | |
| image = cv2.Canny(image, low_threshold, high_threshold) | |
| image = image[:, :, None] | |
| image = np.concatenate([image, image, image], axis=2) | |
| canny_image = Image.fromarray(image) | |
| return canny_image | |
| def generate_images(canvas, prompt): | |
| try: | |
| base64_img = canvas | |
| image_data = base64.b64decode(base64_img.split(',')[1]) | |
| input_img = Image.open(BytesIO(image_data)).convert( | |
| 'RGB').resize((512, 512)) | |
| input_img = input_img.filter(ImageFilter.GaussianBlur(radius=2)) | |
| input_img = get_canny_filter(input_img) | |
| output = pipe( | |
| f'{prompt}, unreal engine, Flickr, Canon camera, f50, best quality, extremely detailed', | |
| input_img, | |
| generator=generator, | |
| num_images_per_prompt=2, | |
| num_inference_steps=20, | |
| negative_prompt="longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality", | |
| ) | |
| all_outputs = [] | |
| for image in output.images: | |
| all_outputs.append(image) | |
| return all_outputs | |
| except Exception as e: | |
| raise gr.Error(str(e)) | |
| def placeholder_fn(axis): | |
| pass | |
| js_change_rotation_axis = """ | |
| async (axis) => { | |
| const poseMakerEl = document.querySelector("pose-maker"); | |
| poseMakerEl.changeRotationAxis(axis); | |
| } | |
| """ | |
| js_pose_template = """ | |
| async (pose) => { | |
| const poseMakerEl = document.querySelector("pose-maker"); | |
| poseMakerEl.setPose(pose); | |
| } | |
| """ | |
| with gr.Blocks(css=share_btn_css) as blocks: | |
| gr.HTML( | |
| """ | |
| <div style="text-align: center; margin: 0 auto;"> | |
| <div | |
| style=" | |
| display: inline-flex; | |
| align-items: center; | |
| gap: 0.8rem; | |
| font-size: 1.75rem; | |
| " | |
| > | |
| <h1 style="font-weight: 900; margin-bottom: 7px;margin-top:5px"> | |
| Pose in 3D & Render with ControlNet (SD-1.5) | |
| </h1> | |
| </div> | |
| <p style="margin-bottom: 10px; font-size: 94%; line-height: 23px;"> | |
| Using <a href="https://huggingface.co./blog/controlnet">ControlNet</a> and <a href="https://boytchev.github.io/mannequin.js/">three.js/mannequin.js</a> | |
| </p> | |
| <p style="margin-bottom: 10px; font-size: 94%; line-height: 23px;"> | |
| For a comprehensive ControlNet-v1.1 demo, checkout <a href="https://huggingface.co./spaces/hysts/ControlNet-v1-1">hysts/ControlNet-v1-1</a> space | |
| </p> | |
| <p>For faster inference without waiting in queue, you may duplicate the space and upgrade to GPU in settings. <a href="https://huggingface.co./spaces/diffusers/controlnet-3d-pose?duplicate=true"><img style="display: inline; margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space" /></a></p> | |
| </div> | |
| """ | |
| ) | |
| with gr.Row(): | |
| with gr.Column(): | |
| canvas = gr.HTML(canvas_html, elem_id="canvas_html", visible=True) | |
| with gr.Row(): | |
| rotation_axis = gr.Radio(["x", "y", "z"], value="x", label="Joint rotation axis") | |
| pose_template = gr.Radio(["regular", "ballet", "handstand", "split", "kick", "chilling"], value="regular", label="Pose template") | |
| prompt = gr.Textbox( | |
| label="Enter your prompt", | |
| max_lines=1, | |
| placeholder="best quality, extremely detailed", | |
| elem_id="prompt", | |
| ) | |
| run_button = gr.Button("Generate") | |
| gr.Markdown("### See an example [here](https://huggingface.co./spaces/diffusers/controlnet-3d-pose/discussions/1)") | |
| with gr.Group(elem_id="share-btn-container"): | |
| community_icon = gr.HTML(community_icon_html) | |
| loading_icon = gr.HTML(loading_icon_html) | |
| share_button = gr.Button("Share to community", elem_id="share-btn") | |
| with gr.Column(): | |
| gallery = gr.Gallery(elem_id="gallery").style(grid=[2], height="auto") | |
| rotation_axis.change(fn=placeholder_fn, | |
| inputs=[rotation_axis], | |
| outputs=[], | |
| queue=False, | |
| _js=js_change_rotation_axis) | |
| pose_template.change(fn=placeholder_fn, | |
| inputs=[pose_template], | |
| outputs=[], | |
| queue=False, | |
| _js=js_pose_template) | |
| run_button.click(fn=generate_images, | |
| inputs=[canvas, prompt], | |
| outputs=[gallery], | |
| _js=get_js_image) | |
| share_button.click(None, [], [], _js=share_js) | |
| blocks.load(None, None, None, _js=load_js) | |
| blocks.launch(debug=True) | |