Instructions to use h94/IP-Adapter-FaceID with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use h94/IP-Adapter-FaceID with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("h94/IP-Adapter-FaceID", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
How to use this with multiple images input?
#38
by alexblattnert - opened
in those examples:
https://huggingface.co/h94/IP-Adapter-FaceID/blob/main/faceid-plus.jpg
https://huggingface.co/h94/IP-Adapter-FaceID/blob/main/faceid_portrait_sd15.jpg
there are no examples on how to recreate them
I'm pretty sure, that for faceid-plus you should use face embeddings from one image and put another one into generate method. And the second one has a demo in a README.md of this repository
could you let me know where to download it?
You can download it from this repo
I could not find an example similar to those images as well.