metadata
license: mit
tags:
- diffusion
- concept-erasure
- stable-diffusion
- stereo
- van_gogh
datasets:
- imagenet
language:
- en
pipeline_tag: text-to-image
stereo_van_gogh
This is a concept-erased Stable Diffusion model using the STEREO method to remove the concept "Van Gogh".
Method
The STEREO method erases concepts from diffusion models.
Usage
from diffusers import StableDiffusionPipeline
import torch
pipe = StableDiffusionPipeline.from_pretrained("ErasureResearch/stereo_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")
Citation
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}
}