---
license: mit
---

# Model Card for EpiDiff

<!-- Provide a quick summary of what the model is/does. -->

[EpiDiff](https://huanngzh.github.io/EpiDiff/) is a generative model based on Zero123 that takes an image of an object as a conditioning frame, and generates 16 multiviews of that object.

![image/gif](https://cdn-uploads.huggingface.co/production/uploads/6375d136dee28348a9c63cbf/EE1-k0Ia8gKxQmCSNfAGF.gif)

## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->



- **Model type:** Generative image-to-multiview model
- **License:** [More Information Needed]

### Model Sources

<!-- Provide the basic links for the model. -->

- **Repository:** https://github.com/huanngzh/EpiDiff
- **Paper:** https://arxiv.org/abs/2312.06725
- **Demo:** https://huanngzh.github.io/EpiDiff/

## Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

For usage instructions, please refer to [our EpiDiff GitHub repository](https://github.com/huanngzh/EpiDiff).

## Training Details

### Training Data

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

We use renders from the LVIS dataset, utilizing [huanngzh/render-toolbox](https://github.com/huanngzh/render-toolbox).