|
|
|
|
|
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') |
|
|
