control_net_canny.py

#!/usr/bin/env python3
import torch
import os
from huggingface_hub import HfApi
from pathlib import Path
from diffusers.utils import load_image
import cv2
from PIL import Image
import numpy as np

from diffusers import (
    ControlNetModel,
    EulerDiscreteScheduler,
    StableDiffusionControlNetPipeline,
    StableDiffusionXLControlNetPipeline,
    UniPCMultistepScheduler,
)
import sys

checkpoint = sys.argv[1]

prompts = [
    "beautiful room",
    "a photo-realistic image of two paradise birds",
    "a snowy house behind a forest",
    "a couple watching a romantic sunset",
    "boats in the Amazonas",
    "a photo of a beautiful face of a woman",
    "a skater in Brooklyn",
    "a tornado in Iowa"
]

sd_xl = "control_v11p" not in checkpoint

if sd_xl:
    base_ckpt = "stabilityai/stable-diffusion-xl-base-0.9"
    controlnet = ControlNetModel.from_pretrained(checkpoint, torch_dtype=torch.float16)
    pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
        base_ckpt, controlnet=controlnet, torch_dtype=torch.float16
    )
    size = 1024
else:
    base_ckpt = "runwayml/stable-diffusion-v1-5"
    controlnet = ControlNetModel.from_pretrained(checkpoint, torch_dtype=torch.float16)
    pipe = StableDiffusionControlNetPipeline.from_pretrained(
        base_ckpt, controlnet=controlnet, torch_dtype=torch.float16
    )
    size = 512

import ipdb; ipdb.set_trace()

# pipe.enable_model_cpu_offload()
pipe.to("cuda")


for i in range(8):
    for seed in range(4):
        image = load_image(
            f"https://huggingface.co/datasets/patrickvonplaten/webdatasets_images/resolve/main/image_{i}.png"
        )
        image = image.resize((size, size))
        prompt = prompts[i]
        image = np.array(image)

        low_threshold = 100
        high_threshold = 200

        image = cv2.Canny(image, low_threshold, high_threshold)
        image = image[:, :, None]
        image = np.concatenate([image, image, image], axis=2)
        canny_image = Image.fromarray(image)

        generator = torch.manual_seed(seed)
        out_image = pipe(prompt, generator=generator, num_inference_steps=20, image=canny_image, controlnet_conditioning_scale=1.0).images[0]

        path = os.path.join(Path.home(), "images", "control_sdxl", f"{i}_{seed}.png")
        path_in_repo = "/".join(path.split("/")[-2:])
        out_image.save(path)

        api = HfApi()

        api.upload_file(
            path_or_fileobj=path,
            path_in_repo=path_in_repo,
            repo_id="patrickvonplaten/images",
            repo_type="dataset",
        )
        print(f"https://huggingface.co/datasets/patrickvonplaten/images/blob/main/control_sdxl/{i}_{seed}.png")