make_reference_image.py

# from https://github.com/lllyasviel/ControlNet/blob/main/gradio_canny2image.py

from share import *
import config

import cv2
import einops
import gradio as gr
import numpy as np
import torch
from PIL import Image

from pytorch_lightning import seed_everything
from annotator.util import resize_image, HWC3
from annotator.canny import apply_canny
from cldm.model import create_model, load_state_dict
from ldm.models.diffusion.ddim import DDIMSampler
from diffusers.utils import load_image

test_prompt = "best quality, extremely detailed, illustration, looking at viewer"
test_negative_prompt = (
    "longbody, lowres, bad anatomy, bad hands, missing fingers, "
    + "pubic hair,extra digit, fewer digits, cropped, worst quality, low quality"
)

canny_edged_image = load_image(
    "https://huggingface.co/takuma104/controlnet_dev/resolve/main/vermeer_canny_edged.png"
)

@torch.no_grad()
def generate(prompt, n_prompt, seed, control, ddim_steps=20, eta=0.0, scale=9.0, H=512, W=512):
    seed_everything(seed)

    cond = {"c_concat": [control], "c_crossattn": [model.get_learned_conditioning([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)
 
    return Image.fromarray(x_samples[0])

if __name__ == '__main__':
    num_samples = 1
    model = create_model('./models/cldm_v15.yaml').cpu()
    model.load_state_dict(load_state_dict('./models/control_sd15_canny.pth', location='cpu'))
    model = model.cuda()
    ddim_sampler = DDIMSampler(model)

    control = torch.from_numpy(np.array(canny_edged_image).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()

    for seed in range(4):
        image = generate(test_prompt, test_negative_prompt, seed=seed, control=control)
        image.save(f'vermeer_canny_edged_seed_{seed}.png')