| |
|
|
| import einops |
| import numpy as np |
| import torch |
| from PIL import Image |
| import sys |
| import os |
| import yaml |
|
|
| CONTROL_NET_PATH = '/home/takuma/Documents/co/ControlNet-v1-1-nightly/' |
| CONTROL_NET_MODEL_PATH = '../../ControlNet-v1-1' |
| sys.path.append(CONTROL_NET_PATH) |
|
|
| from share import * |
| from pytorch_lightning import seed_everything |
| from cldm.model import create_model, load_state_dict |
| from cldm.ddim_hacked import DDIMSampler |
| from diffusers.utils import load_image |
|
|
| test_prompt = "best quality, extremely detailed" |
| test_negative_prompt = "blur, lowres, bad anatomy, worst quality, low quality" |
|
|
| @torch.no_grad() |
| def generate(prompt, n_prompt, seed, control, image, ddim_steps=20, eta=0.0, scale=9.0, H=512, W=512, strength = 1.0, guess_mode=False, denoise_strength=1.0): |
| seed_everything(seed) |
|
|
| cond = {"c_concat": [control], "c_crossattn": [model.get_learned_conditioning([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) |
|
|
| noise = torch.randn((1,) + shape, device="cpu", generator=torch.Generator(device="cpu").manual_seed(seed)).cuda() |
|
|
| ddim_sampler.make_schedule(ddim_steps, ddim_eta=eta, verbose=True) |
| t_enc = min(int(denoise_strength * ddim_steps), ddim_steps - 1) |
| z = model.get_first_stage_encoding(model.encode_first_stage(image)) |
| z_enc = ddim_sampler.stochastic_encode(z, torch.tensor([t_enc] * num_samples).to(model.device), noise=noise) |
|
|
| model.control_scales = [strength * (0.825 ** float(12 - i)) for i in range(13)] if guess_mode else ([strength] * 13) |
|
|
| samples = ddim_sampler.decode(z_enc, cond, t_enc, 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) |
| |
| return Image.fromarray(x_samples[0]) |
|
|
| def control_images(control_image_folder, model_name): |
| with open('./control_images.yaml', 'r') as f: |
| d = yaml.safe_load(f) |
| filenames = d[model_name] |
| return [Image.open(f'{control_image_folder}/{fn}').convert("RGB") for fn in filenames] |
|
|
| def resize_for_condition_image(input_image: Image, resolution: int): |
| input_image = input_image.convert("RGB") |
| W, H = input_image.size |
| k = float(resolution) / min(H, W) |
| H *= k |
| W *= k |
| H = int(round(H / 64.0)) * 64 |
| W = int(round(W / 64.0)) * 64 |
| img = input_image.resize((W, H), resample=Image.LANCZOS if k > 1 else Image.AREA) |
| return img |
|
|
| if __name__ == '__main__': |
| model_name = "f1e_sd15_tile" |
|
|
| original_image_folder = "./control_images/" |
| control_image_folder = './control_images/converted/' |
| output_image_folder = './output_images/ref/' |
| os.makedirs(output_image_folder, exist_ok=True) |
|
|
| if model_name == 'p_sd15s2_lineart_anime': |
| base_model_file = 'anything-v3-full.safetensors' |
| else: |
| base_model_file = 'v1-5-pruned.ckpt' |
|
|
| num_samples = 1 |
| model = create_model(f'{CONTROL_NET_MODEL_PATH}/control_v11{model_name}.yaml').cpu() |
| model.load_state_dict(load_state_dict(f'{CONTROL_NET_PATH}/models/{base_model_file}', location='cuda'), strict=False) |
| model.load_state_dict(load_state_dict(f'{CONTROL_NET_MODEL_PATH}/control_v11{model_name}.pth', location='cuda'), strict=False) |
| model = model.cuda() |
| ddim_sampler = DDIMSampler(model) |
|
|
| original_image_filenames = [ |
| "dog_64x64.png", |
| ] |
|
|
| image_conditions = [ |
| resize_for_condition_image( |
| Image.open(f"{original_image_folder}{fn}"), |
| resolution=512, |
| ) |
| for fn in original_image_filenames |
| ] |
|
|
|
|
| for i, control_image in enumerate(image_conditions): |
| control = np.array(control_image).copy() |
| control = torch.from_numpy(control).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() |
|
|
| img = np.array(control_image).copy() |
| img = torch.from_numpy(img).float().cuda() / 127.0 - 1.0 |
| img = torch.stack([img for _ in range(num_samples)], dim=0) |
| img = einops.rearrange(img, 'b h w c -> b c h w').clone() |
|
|
| for seed in range(4): |
| image = generate(test_prompt, test_negative_prompt, seed=seed, control=control, image=img) |
| image.save(f'{output_image_folder}output_{model_name}_{i}_{seed}.png') |
|
|
