Text-to-Image
Diffusers
English
image-generation
subject-personalization
style-transfer
Diffusion-Transformer
Instructions to use bytedance-research/USO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use bytedance-research/USO 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-research/USO", 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 Settings
- Draw Things
- DiffusionBee
Update pipeline tag to text-to-image and add Hugging Face paper link
#3
by nielsr HF Staff - opened
This PR improves the model card by:
- Updating the
pipeline_tagfromimage-to-imagetotext-to-image. This change accurately reflects the model's capability to generate images from text descriptions, even when image inputs are used for conditioning. This will improve discoverability at https://huggingface.co/models?pipeline_tag=text-to-image. - Adding a direct link to the Hugging Face paper page (USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning) for easier access to the research paper.
- Removing the redundant `
fenfan changed pull request status to merged