Text-to-Image
Diffusers
Safetensors
English
StableDiffusionPipeline
diffusion
concept-erasure
stable-diffusion
ga
english_springer_spaniel
Instructions to use DiffusionConceptErasure/ga_english_springer_spaniel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use DiffusionConceptErasure/ga_english_springer_spaniel with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("DiffusionConceptErasure/ga_english_springer_spaniel", 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
- Local Apps
- Draw Things
- DiffusionBee
ga_english_springer_spaniel
This is a concept-erased Stable Diffusion model using the Gradient Ascent (GA) method to remove the concept "English Springer Spaniel".
Method
Gradient Ascent (GA) actively pushes the model away from generating the target concept.
Usage
from diffusers import StableDiffusionPipeline
import torch
pipe = StableDiffusionPipeline.from_pretrained("ErasureResearch/ga_english_springer_spaniel", torch_dtype=torch.float16).to("cuda")
prompt = "a photo of a english_springer_spaniel"
image = pipe(prompt).images[0]
image.save("erased_english_springer_spaniel.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}
}
- Downloads last month
- -