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
Image distortion when loading plus lora
#24
by aguang - opened
Thanks for sharing how to load face id's lora file, I was using the same method to load ip-adapter-faceid-plus_sd15_lora and the images generated were terrible. The code to load is as follows:
ip_ckpt = "ip-adapter-faceid-plus_sd15.bin"
lora_ckpt = "ip-adapter-faceid-plus_sd15_lora.safetensors"
...
pipe.load_lora_weights(lora_ckpt)
pipe.fuse_lora()
ip_model = IPAdapterFaceIDPlus(pipe, image_encoder_path, ip_ckpt, device)
Is there any problem with the above code please? Or the same method doesn't work with the plus lora?