Downloads · 30 days
1
5% of all-time downloads
DiffusionConceptErasure/ga_parachute
ga_parachute 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 Gradient Ascent (GA) method to remove the concept "Parachute".
Downloads · 30 days
1
5% of all-time downloads
All-time downloads
19
Public
Parameters
860M
3.9 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors3.9 GB · 100%
From the Hugging Face model README
This is a concept-erased Stable Diffusion model using the Gradient Ascent (GA) method to remove the concept "Parachute".
Gradient Ascent (GA) actively pushes the model away from generating the target concept.
from diffusers import StableDiffusionPipeline
import torch
pipe = StableDiffusionPipeline.from_pretrained("ErasureResearch/ga_parachute", torch_dtype=torch.float16).to("cuda")
prompt = "a photo of a parachute"
image = pipe(prompt).images[0]
image.save("erased_parachute.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}
}