Instructions to use TencentARC/PhotoMaker with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use TencentARC/PhotoMaker with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("TencentARC/PhotoMaker", 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
What is the difference between this solution and IP-Adapter-Face-ID ?
#2
by MohamedRashad - opened
What is the difference between this solution and IP-Adapter-Face-ID ?
I'd like to know too.
PhotoMaker: Stacked ID embedding + updated text embedding + tuned encoder + LoRA modules, publish date: December 7th,2023
IP-Adapter-Face-ID: tuned face encoder + LoRA modules, publish date: December 20th,2023
This comment has been hidden
You can see that there are more and more methods to improve ID fidelity by extracting the embedding of multiple images including ID-Adapter-FaceID and InstantID.