from share import * import config import cv2 import einops import gradio as gr import numpy as np import torch import random from pytorch_lightning import seed_everything from annotator.util import resize_image, HWC3 from cldm.model import create_model, load_state_dict from cldm.ddim_hacked import DDIMSampler import dlib from PIL import Image, ImageDraw if torch.cuda.is_available(): device = torch.device("cuda") else: device = torch.device("cpu") model = create_model('./models/cldm_v15.yaml').cpu() model.load_state_dict(load_state_dict('./models/control_sd15_landmarks.pth', location='cpu')) model = model.to(device) ddim_sampler = DDIMSampler(model) detector = dlib.get_frontal_face_detector() predictor = dlib.shape_predictor("shape_predictor_68_face_landmarks.dat") def draw_landmarks(image, landmarks, color="white", radius=2.5): draw = ImageDraw.Draw(image) for dot in landmarks: x, y = dot draw.ellipse((x-radius, y-radius, x+radius, y+radius), fill=color) def get_68landmarks_img(img): gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY) faces = detector(gray) landmarks = [] for face in faces: shape = predictor(gray, face) for i in range(68): x = shape.part(i).x y = shape.part(i).y landmarks.append((x, y)) con_img = Image.new('RGB', (img.shape[1], img.shape[0]), color=(0, 0, 0)) draw_landmarks(con_img, landmarks) con_img = np.array(con_img) return con_img def process(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, guess_mode, landmark_direct_mode, strength, scale, seed, eta): with torch.no_grad(): img = resize_image(HWC3(input_image), image_resolution) H, W, C = img.shape if landmark_direct_mode: detected_map = img else: detected_map = get_68landmarks_img(img) detected_map = HWC3(detected_map) control = torch.from_numpy(detected_map.copy()).float().to(device) / 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() if seed == -1: seed = random.randint(0, 65535) seed_everything(seed) if config.save_memory: model.low_vram_shift(is_diffusing=False) cond = {"c_concat": [control], "c_crossattn": [model.get_learned_conditioning([prompt + ', ' + a_prompt] * num_samples)]} un_cond = {"c_concat": None if guess_mode else [control], "c_crossattn": [model.get_learned_conditioning([n_prompt] * num_samples)]} shape = (4, H // 8, W // 8) if config.save_memory: model.low_vram_shift(is_diffusing=True) model.control_scales = [strength * (0.825 ** float(12 - i)) for i in range(13)] if guess_mode else ([strength] * 13) # Magic number. IDK why. Perhaps because 0.825**12<0.01 but 0.826**12>0.01 samples, intermediates = ddim_sampler.sample(ddim_steps, num_samples, shape, cond, verbose=False, eta=eta, unconditional_guidance_scale=scale, unconditional_conditioning=un_cond) if config.save_memory: model.low_vram_shift(is_diffusing=False) 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() with block: with gr.Row(): gr.Markdown("## Control Stable Diffusion with Face Landmarks") with gr.Row(): with gr.Column(): input_image = gr.Image(source='upload', type="numpy") 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=64) strength = gr.Slider(label="Control Strength", minimum=0.0, maximum=2.0, value=1.0, step=0.01) guess_mode = gr.Checkbox(label='Guess Mode', value=False) landmark_direct_mode = gr.Checkbox(label='Input Landmark Directly', value=False) 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=-1, 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='cartoon, disfigured, bad art, deformed, poorly drawn, extra limbs, weird colors, blurry, lowres, bad anatomy, bad hands, missing fingers, 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, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, guess_mode, landmark_direct_mode, strength, scale, seed, eta] run_button.click(fn=process, inputs=ips, outputs=[result_gallery]) block.launch()