gen_compare/gen_diffusers_image.py

# Diffusers' ControlNet Implementation Subjective Evaluation
# https://github.com/takuma104/diffusers/tree/controlnet

import einops
import numpy as np
import torch
import sys

from diffusers import StableDiffusionControlNetPipeline

from PIL import Image

test_prompt = "best quality, extremely detailed"
test_negative_prompt = "lowres, bad anatomy, worst quality, low quality"

def generate_image(seed, control):
    latent = torch.randn((1,4,64,64), device="cpu", generator=torch.Generator(device="cpu").manual_seed(seed)).cuda()
    image = pipe(
        prompt=test_prompt,
        negative_prompt=test_negative_prompt,
        guidance_scale=9.0,
        num_inference_steps=20,
        latents=latent,
        #generator=torch.Generator(device="cuda").manual_seed(seed),
        image=control,
    ).images[0]
    return image

if __name__ == '__main__':
    model_name = sys.argv[1]
    control_image_folder = './control_images/converted/'
    output_image_folder = './output_images/diffusers/'
    model_id = f'../../control_sd15_{model_name}'

    pipe = StableDiffusionControlNetPipeline.from_pretrained(model_id).to("cuda")
    #pipe.enable_attention_slicing(1)

    image_types = {'bird', 'human', 'room', 'vermeer'}

    for image_type in image_types:
        control_image = Image.open(f'{control_image_folder}control_{image_type}_{model_name}.png')
        control = np.array(control_image)[:,:,::-1].copy()
        control = torch.from_numpy(control).float().cuda() / 255.0
        control = torch.stack([control for _ in range(1)], dim=0)
        control = einops.rearrange(control, 'b h w c -> b c h w').clone()

        for seed in range(4):
            image = generate_image(seed=seed, control=control)
            image.save(f'{output_image_folder}output_{image_type}_{model_name}_{seed}.png')