Instructions to use CiaraRowles/IP-Adapter-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use CiaraRowles/IP-Adapter-Instruct 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("CiaraRowles/IP-Adapter-Instruct", 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
Link models to paper
#1
by nielsr HF Staff - opened
This PR ensures the models can be viewed from https://huggingface.co/papers/2408.03209.
Cheers,
Niels
Open-source @ HF
<3
CiaraRowles changed pull request status to merged
Thanks for merging @CiaraRowles !
Btw to make download metrics work, the diffusers tag would need to be added and the weights would need to converted to safetensors.
I need to check if the finished model still has the shared tensors like the original checkpoint as that broke the original checkpoint with safetensors