tools / controlnet_img2img.py
patrickvonplaten's picture
up
5f12b41
raw
history blame
2.47 kB
#!/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,
StableDiffusionControlNetImg2ImgPipeline,
StableDiffusionControlNetInpaintPipeline,
DiffusionPipeline,
UniPCMultistepScheduler,
)
import sys
checkpoint = sys.argv[1]
# image = load_image(
# "https://huggingface.co/lllyasviel/sd-controlnet-canny/resolve/main/images/bird.png"
# )
img_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png"
mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png"
image = load_image(img_url).resize((512, 512))
mask_image = load_image(mask_url).resize((512, 512))
np_image = np.array(image)
low_threshold = 100
high_threshold = 200
np_image = cv2.Canny(np_image, low_threshold, high_threshold)
np_image = np_image[:, :, None]
np_image = np.concatenate([np_image, np_image, np_image], axis=2)
canny_image = Image.fromarray(np_image)
controlnet = ControlNetModel.from_pretrained(checkpoint, torch_dtype=torch.float16)
# pipe = DiffusionPipeline.from_pretrained(
# "runwayml/stable-diffusion-inpainting", controlnet=controlnet, torch_dtype=torch.float16, custom_pipeline="stable_diffusion_controlnet_inpaint"
# )
pipe = StableDiffusionControlNetInpaintPipeline.from_pretrained(
"runwayml/stable-diffusion-inpainting",
controlnet=controlnet,
torch_dtype=torch.float16,
)
pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
pipe.enable_model_cpu_offload()
generator = torch.manual_seed(0)
text_prompt="a blue dog"
# out_image = pipe("A blue dog", num_inference_steps=50, generator=generator, image=image, mask_image=mask_image, controlnet_conditioning_image=canny_image).images[0]
out_image = pipe(
text_prompt,
num_inference_steps=20,
generator=generator,
image=image,
mask_image=mask_image,
control_image=canny_image,
).images[0]
path = os.path.join(Path.home(), "images", "aa.png")
out_image.save(path)
api = HfApi()
api.upload_file(
path_or_fileobj=path,
path_in_repo=path.split("/")[-1],
repo_id="patrickvonplaten/images",
repo_type="dataset",
)
print("https://huggingface.co/datasets/patrickvonplaten/images/blob/main/aa.png")