SPEED

Here are the released model checkpoints of our paper:

SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models

teaser

Three characteristics of our proposed method, SPEED. (a) Scalable: SPEED seamlessly scales from single-concept to large-scale multi-concept erasure (e.g., 100 celebrities) without additional design. (b) Precise: SPEED precisely removes the target concept (e.g., Snoopy) while preserving the semantic integrity for non-target concepts (e.g., Hello Kitty and SpongeBob). (c) Efficient: SPEED can immediately erase 100 concepts within 5 seconds, achieving a ×350 speedup over the state-of-the-art (SOTA) method.

More implementation details can refer to our GitHub repository.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Model tree for lioooox/SPEED

Finetuned
(1102)
this model