Downloads · 30 days
8
20% of all-time downloads
DiffusionConceptErasure/uce_van_gogh
uce_van_gogh is a text-to-image model from DiffusionConceptErasure. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as mit.
This is a concept-erased Stable Diffusion model using the Unlearning via Concept Erasure (UCE) method to remove the concept "Van Gogh".
Downloads · 30 days
8
20% of all-time downloads
All-time downloads
40
Public
Parameters
860M
5.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors5.5 GB · 100%
From the Hugging Face model README
This is a concept-erased Stable Diffusion model using the Unlearning via Concept Erasure (UCE) method to remove the concept "Van Gogh".
Unlearning via Concept Erasure (UCE) modifies the model's internal representations to remove specific concept knowledge.
from diffusers import StableDiffusionPipeline
import torch
pipe = StableDiffusionPipeline.from_pretrained("ErasureResearch/uce_van_gogh", torch_dtype=torch.float16).to("cuda")
prompt = "a photo of a van_gogh"
image = pipe(prompt).images[0]
image.save("erased_van_gogh.png")
If you use this model in your research, please cite:
@article{concept_erasure_2024,
title={Concept Erasure in Diffusion Models},
author={ErasureResearch Team},
journal={Proceedings of...},
year={2024}
}