Instructions to use ByteDance/ID-Patch with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ByteDance/ID-Patch with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ByteDance/ID-Patch", 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
| license: openrail++ | |
| # Model Card for ID-Patch | |
| <!-- Provide a quick summary of what the model is/does. --> | |
| ID-Patch is a diffusion model capable of generating ID-preserving group photos | |
| ## Model Details | |
| Please refer our github repository for more details and how to use this model. | |
| - **Repository:** https://github.com/bytedance/ID-Patch | |
| - **Paper:** https://arxiv.org/abs/2411.13632 | |
| ## License | |
| The model is released under [CreativeML Open RAIL++-M License](https://huggingface.co/ByteDance/ID-Patch/blob/main/LICENSE.md) |