Instructions to use ByteDance/XVerse with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ByteDance/XVerse 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/XVerse", 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
Improve model card: Add metadata, project page, abstract, and usage examples
#2
by nielsr HF Staff - opened
This PR significantly enhances the model card for XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation.
Key changes include:
- Adding
pipeline_tag: text-to-imagefor improved discoverability on the Hub (e.g., https://huggingface.co/models?pipeline_tag=text-to-image). - Specifying
library_name: diffusersfor better integration with the Hugging Face ecosystem. - Including a link to the official project page (
https://bytedance.github.io/XVerse). - Incorporating the paper abstract for quick understanding of the model's contribution.
- Expanding the model card content with a detailed introduction, a comprehensive quick start guide for local Gradio demo, and instructions for inference with XVerseBench, all directly from the official GitHub repository.
- Adding the official image and full license details from the GitHub repository.
This update makes the model much more informative and user-friendly for researchers and practitioners on Hugging Face.