Instructions to use FudanCVL/EffectErase with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use FudanCVL/EffectErase 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/EffectErase", 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
Commit History
-
Update model card with paper links and improved metadata
Verified signatureHi! I'm Niels from the community science team at Hugging Face. This PR improves the model card for **EffectErase** by: - Linking the repository to the official paper [2603.19224](https://huggingface.co/papers/2603.19224). - Updating the metadata with specific tags for video object removal and inpainting to make the model easier to find. - Refining the README to ensure all links (Project Page, GitHub, arXiv) point to the correct resources. - Cleaning up the abstract for better readability.51f3167
-
Update README.md
Verified signaturec3c096d -
Update README.md
Verified signature0f5a322 -
Update README.md
Verified signature691bef1 -
Update README.md
Verified signaturecccc80e -
Upload assets/teaser.gif
Verified signatureef0171f -
Update README.md
Verified signature9af0a4c -
Update README.md
Verified signaturedb5b29c -
Create README.md
Verified signaturee7cedbd -
Upload EffectErase.ckpt with huggingface_hub
Verified signatureaf6baee -
initial commit
Verified signature53c1ad7