| import cv2 | |
| import einops | |
| import gradio as gr | |
| import numpy as np | |
| import torch | |
| from cldm.hack import disable_verbosity | |
| disable_verbosity() | |
| from pytorch_lightning import seed_everything | |
| from annotator.util import resize_image, HWC3 | |
| from annotator.midas import apply_midas | |
| from cldm.model import create_model, load_state_dict | |
| from ldm.models.diffusion.ddim import DDIMSampler | |
| def process_depth(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, detect_resolution, ddim_steps, scale, seed, eta, model, ddim_sampler): | |
| with torch.no_grad(): | |
| input_image = HWC3(input_image) | |
| detected_map, _ = apply_midas(resize_image(input_image, detect_resolution)) | |
| detected_map = HWC3(detected_map) | |
| img = resize_image(input_image, image_resolution) | |
| H, W, C = img.shape | |
| detected_map = cv2.resize(detected_map, (W, H), interpolation=cv2.INTER_LINEAR) | |
| 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) | |
| 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 [detected_map] + results | |