You are viewing v0.5.1 version.
A newer version
v0.31.0 is available.
Text-Guided Image-Inpainting
The StableDiffusionInpaintPipeline lets you edit specific parts of an image by providing a mask and text prompt.
from io import BytesIO
import requests
import PIL
from diffusers import StableDiffusionInpaintPipeline
def download_image(url):
response = requests.get(url)
return PIL.Image.open(BytesIO(response.content)).convert("RGB")
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"
init_image = download_image(img_url).resize((512, 512))
mask_image = download_image(mask_url).resize((512, 512))
device = "cuda"
pipe = StableDiffusionInpaintPipeline.from_pretrained(
"CompVis/stable-diffusion-v1-4", revision="fp16", torch_dtype=torch.float16
).to(device)
prompt = "a cat sitting on a bench"
images = pipe(prompt=prompt, init_image=init_image, mask_image=mask_image, strength=0.75).images
images[0].save("cat_on_bench.png")