---
license: apache-2.0
library_name: diffusers
tags:
- relighting
- indoor
- video-diffusion
base_model: stabilityai/stable-video-diffusion-img2vid-xt
pipeline_tag: image-to-image
---

# LightShift

**LightShift: Controllable Indoor Relighting via Video Diffusion Priors**

This repository contains the fine-tuned UNet checkpoint for LightShift, a controllable indoor relighting method that repurposes Stable Video Diffusion for image-based relighting.

## Usage

This checkpoint is compatible with the [Diffusers](https://github.com/huggingface/diffusers) library. See the code and inference scripts at [Pensioner-11/LightShift](https://github.com/Pensioner-11/LightShift).

```python
from diffusers import StableVideoDiffusionPipeline

pipe = StableVideoDiffusionPipeline.from_pretrained(
    "Pensioner/LightShift",
    torch_dtype=torch.float16,
).to("cuda")
```

## Model Description

- **Base model:** [stabilityai/stable-video-diffusion-img2vid-xt](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt)
- **Fine-tuned component:** UNet
- **Training steps:** 200,000

## Citation

Citation information will be updated after publication.