Spaces:
Build error
Build error
| import cv2 | |
| import einops | |
| import gradio as gr | |
| import numpy as np | |
| import torch | |
| from pytorch_lightning import seed_everything | |
| from util import resize_image, HWC3, apply_canny | |
| from ldm.models.diffusion.ddim import DDIMSampler | |
| from annotator.openpose import apply_openpose | |
| from cldm.model import create_model, load_state_dict | |
| from huggingface_hub import hf_hub_url, cached_download | |
| REPO_ID = "lllyasviel/ControlNet" | |
| scribble_checkpoint = "models/control_sd15_scribble.pth" | |
| scribble_model = create_model('./models/cldm_v15.yaml').cpu() | |
| scribble_model.load_state_dict(load_state_dict(cached_download( | |
| hf_hub_url(REPO_ID, scribble_checkpoint) | |
| ), location='cpu')) | |
| scribble_model = scribble_model.cuda() | |
| ddim_sampler_scribble = DDIMSampler(scribble_model) | |
| save_memory = False | |
| def process(input_image, prompt, input_control, num_samples, image_resolution, ddim_steps, scale, seed, eta, low_threshold, high_threshold): | |
| # TODO: Clean Function for single Task | |
| if input_control == "Scribble": | |
| return process_scribble(input_image, prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta) | |
| def process_scribble(input_image, prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta): | |
| with torch.no_grad(): | |
| img = resize_image(HWC3(input_image), image_resolution) | |
| H, W, C = img.shape | |
| detected_map = np.zeros_like(img, dtype=np.uint8) | |
| detected_map[np.min(img, axis=2) < 127] = 255 | |
| control = torch.from_numpy(detected_map.copy()).float().cuda() / 255.0 | |
| control = torch.stack([control for _ in range(num_samples)], dim=0) | |
| control = einops.rearrange(control, 'b h w c -> b c h w').clone() | |
| seed_everything(seed) | |
| if save_memory: | |
| scribble_model.low_vram_shift(is_diffusing=False) | |
| cond = {"c_concat": [control], "c_crossattn": [scribble_model.get_learned_conditioning([prompt + ', ' + a_prompt] * num_samples)]} | |
| un_cond = {"c_concat": [control], "c_crossattn": [scribble_model.get_learned_conditioning([n_prompt] * num_samples)]} | |
| shape = (4, H // 8, W // 8) | |
| if save_memory: | |
| scribble_model.low_vram_shift(is_diffusing=False) | |
| samples, intermediates = ddim_sampler_scribble.sample(ddim_steps, num_samples, | |
| shape, cond, verbose=False, eta=eta, | |
| unconditional_guidance_scale=scale, | |
| unconditional_conditioning=un_cond) | |
| if save_memory: | |
| scribble_model.low_vram_shift(is_diffusing=False) | |
| x_samples = scribble_model.decode_first_stage(samples) | |
| x_samples = (einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 + 127.5).cpu().numpy().clip(0, 255).astype(np.uint8) | |
| results = [x_samples[i] for i in range(num_samples)] | |
| return [255 - detected_map] + results | |
| def create_canvas(w, h): | |
| new_control_options = ["Interactive Scribble"] | |
| return np.zeros(shape=(h, w, 3), dtype=np.uint8) + 255 | |
| block = gr.Blocks().queue() | |
| control_task_list = [ | |
| "Scribble" | |
| ] | |
| a_prompt = 'best quality, extremely detailed, architecture render, photorealistic, hyper realistic, surreal, dali, 3d rendering, render, 8k, 16k, extremely detailed, unreal engine, octane, maya' | |
| n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, pubic hair,extra digit, number, text, watermark, fewer digits, cropped, worst quality, low quality' | |
| with block: | |
| gr.Markdown("## ControlNet - Architectural Sketch to Render Image") | |
| gr.HTML(''' | |
| <p style="margin-bottom: 10px; font-size: 94%"> | |
| Demo for ControlNet, Optimized for architectural sketch, based on <a href="https://github.com/lllyasviel/ControlNet" style="text-decoration: underline;" target="_blank"> lllyasviel ControlNet </a> implementation. | |
| </p> | |
| ''') | |
| gr.HTML(''' | |
| <p style="margin-bottom: 8px; font-size: 94%"> | |
| HF Space created by Thaweewat Rugsujarit, If you have any suggestions or feedback, please feel free to contact me via <a href="https://www.linkedin.com/in/thaweewat-rugsujarit/" style="text-decoration: underline;" target="_blank"> Linkedin </a>. | |
| </p> | |
| ''') | |
| with gr.Row(): | |
| with gr.Column(): | |
| input_image = gr.Image(source='upload', type="numpy") | |
| input_control = gr.Dropdown(control_task_list, value="Scribble", label="Task") | |
| prompt = gr.Textbox(label="Architectural Style") | |
| run_button = gr.Button(label="Run") | |
| with gr.Accordion("Advanced options", open=False): | |
| num_samples = gr.Slider(label="Images", minimum=1, maximum=12, value=1, step=1) | |
| image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=256) | |
| low_threshold = gr.Slider(label="Canny low threshold", minimum=1, maximum=255, value=100, step=1) | |
| high_threshold = gr.Slider(label="Canny high threshold", minimum=1, maximum=255, value=200, step=1) | |
| ddim_steps = gr.Slider(label="Steps", minimum=1, maximum=100, value=20, step=1) | |
| scale = gr.Slider(label="Guidance Scale", minimum=0.1, maximum=30.0, value=9.0, step=0.1) | |
| seed = gr.Slider(label="Seed", minimum=0, maximum=2147483647, step=1, randomize=True) | |
| eta = gr.Slider(label="eta (DDIM)", minimum=0.0,maximum =1.0, value=0.0, step=0.1) | |
| with gr.Column(): | |
| result_gallery = gr.Gallery(label='Output', show_label=False, elem_id="gallery").style(grid=2, height='auto') | |
| ips = [input_image, prompt, input_control, num_samples, image_resolution, ddim_steps, scale, seed, eta, low_threshold, high_threshold] | |
| run_button.click(fn=process, inputs=ips, outputs=[result_gallery]) | |
| gr.Markdown("") | |
| block.launch(debug = True) |