---
license: mit
tags:
- diffusion
- concept-erasure
- stable-diffusion
- uce
- garbage_truck
datasets:
- imagenet
language:
- en
pipeline_tag: text-to-image
---

# uce_garbage_truck

This is a concept-erased Stable Diffusion model using the **Unlearning via Concept Erasure (UCE)** method to remove the concept **"Garbage Truck"**.

## Method

Unlearning via Concept Erasure (UCE) modifies the model's internal representations to remove specific concept knowledge.

## Usage

```python
from diffusers import StableDiffusionPipeline
import torch

pipe = StableDiffusionPipeline.from_pretrained("ErasureResearch/uce_garbage_truck", torch_dtype=torch.float16).to("cuda")
prompt = "a photo of a garbage_truck"
image = pipe(prompt).images[0]
image.save("erased_garbage_truck.png")
```

## Citation

If you use this model in your research, please cite:

```bibtex
@article{concept_erasure_2024,
  title={Concept Erasure in Diffusion Models},
  author={ErasureResearch Team},
  journal={Proceedings of...},
  year={2024}
}
```