Instructions to use FudanCVL/OcclusionFormer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use FudanCVL/OcclusionFormer with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("FudanCVL/OcclusionFormer", 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
Update model card metadata, links and usage instructions
#1
by nielsr HF Staff - opened
Hi, I'm Niels from the community science team at Hugging Face. I've updated your model card to improve its visibility and usability:
- Updated placeholder badges for arXiv and ICML 2026 with the actual project links.
- Added
base_modelanddatasetsmetadata to link this repository to the FLUX model and the SA-Z dataset. - Included the CLI and Streamlit inference instructions from your GitHub README to provide a "Quick Start" guide for users.
- Linked the paper to the Hugging Face papers page.