Image-to-Image
Diffusers
StableDiffusionInpaintPipeline
stable-diffusion
stable-diffusion-diffusers
text-guided-to-image-inpainting
endpoints-template
Instructions to use philschmid/stable-diffusion-2-inpainting-endpoint with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use philschmid/stable-diffusion-2-inpainting-endpoint with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("philschmid/stable-diffusion-2-inpainting-endpoint", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
StableDiffusionPipeline not working
#2
by hoeirup32 - opened
Cant deploy this endpoint anylonger, get some error with the pipeline. Might be caused by the custom handler and Pipeline set up. Have tried custom handler as well
What is the error you are seeing?
Can you retry?
For some reasons it running now, thanks.
Tried like 8 times yesterday :D
hoeirup32 changed discussion status to closed
I made a change in the requirements.txt which was using an old version.
