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 cldm.model import create_model, load_state_dict from huggingface_hub import hf_hub_url, cached_download REPO_ID = "lllyasviel/ControlNet" FILENAME = "models/control_sd15_canny.pth" model = create_model('./models/cldm_v15.yaml') model.load_state_dict(load_state_dict(cached_download( hf_hub_url(REPO_ID, FILENAME) ), location='cpu')) ddim_sampler = DDIMSampler(model) def process(input_image, prompt, input_control, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta, low_threshold, high_threshold): # TODO: Add other control tasks return process_canny(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta, low_threshold, high_threshold) def process_canny(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta, low_threshold, high_threshold): with torch.no_grad(): img = resize_image(HWC3(input_image), image_resolution) H, W, C = img.shape detected_map = apply_canny(img, low_threshold, high_threshold) detected_map = HWC3(detected_map) control = torch.from_numpy(detected_map.copy()).float() / 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) cond = {"c_concat": [control], "c_crossattn": [model.get_learned_conditioning([prompt + ', ' + a_prompt] * num_samples)]} un_cond = {"c_concat": [control], "c_crossattn": [model.get_learned_conditioning([n_prompt] * num_samples)]} shape = (4, H // 8, W // 8) samples, intermediates = ddim_sampler.sample(ddim_steps, num_samples, shape, cond, verbose=False, eta=eta, unconditional_guidance_scale=scale, unconditional_conditioning=un_cond) x_samples = 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 block = gr.Blocks().queue() control_task_list = [ "Canny Edge Map", "Human Pose" ] with block: gr.Markdown("## Adding Conditional Control to Text-to-Image Diffusion Models") with gr.Row(): with gr.Column(): input_image = gr.Image(source='upload', type="numpy") input_control = gr.Dropdown(control_list, value="Canny Edge Map", label="Control Task"), prompt = gr.Textbox(label="Prompt") 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.Number(label="eta (DDIM)", value=0.0) a_prompt = gr.Textbox(label="Added Prompt", value='best quality, extremely detailed') n_prompt = gr.Textbox(label="Negative Prompt", value='longbody, lowres, bad anatomy, bad hands, missing fingers, pubic hair,extra digit, fewer digits, cropped, worst quality, low quality') 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, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta, low_threshold, high_threshold] run_button.click(fn=process, inputs=ips, outputs=[result_gallery]) examples = gr.Examples(examples=[["bird.png", "bird","Canny Edge Map"]],inputs = [input_image, prompt, input_control], outputs = [result_gallery]) block.launch(debug = True)