| 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 cldm.model import create_model, load_state_dict |
| from ldm.models.diffusion.ddim import DDIMSampler |
|
|
| def process(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta): |
| with torch.no_grad(): |
| img = resize_image(HWC3(input_image['mask'][:, :, 0]), 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) |
|
|
| 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 |
|
|
|
|
| def create_canvas(w, h): |
| return np.zeros(shape=(h, w, 3), dtype=np.uint8) + 255 |
|
|
