Instructions to use yujieouo/G2RPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use yujieouo/G2RPO with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("yujieouo/G2RPO", 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 pipeline tag, library name, paper and project links
#1
by nielsr HF Staff - opened
This PR enhances the model card for G²RPO by adding essential metadata and links:
- Adds
pipeline_tag: text-to-imageto improve model discoverability on the Hub. - Adds
library_name: diffusers, enabling the automated "How to use" widget for Diffusers. - Adds an explicit link to the Hugging Face paper page: $\text{G}^2$RPO: Granular GRPO for Precise Reward in Flow Models.
- Includes a link to the project page: https://bujiazi.github.io/g2rpo.github.io/.
- Adds the "Citation" and "Acknowledgement" sections from the GitHub repository to complete the documentation.
These additions will make the model more accessible and informative for users.
yujieouo changed pull request status to merged