README.md

---
tags:
- Image-to-3D
- Image-to-4D
- GenXD
language:
- en
- zh
base_model:
- stabilityai/stable-video-diffusion-img2vid-xt
pipeline_tag: image-to-3d
license: apache-2.0
datasets:
- Yuyang-z/CamVid-30K
---

# GenXD Model Card

<p align="center" style="border-radius: 10px">
  <img src="https://gen-x-d.github.io/materials/figures/icon.jpg" width="35%" alt="logo"/>
</p>

<div style="display:flex;justify-content: center">
  <a href="https://huggingface.co/Yuyang-z/genxd"><img src="https://img.shields.io/static/v1?label=Weights&message=Huggingface&color=yellow"></a> &ensp;
  <a href="https://github.com/HeliosZhao/GenXD"><img src="https://img.shields.io/static/v1?label=Code&message=Github&color=blue&logo=github"></a> &ensp;
  <a href="https://gen-x-d.github.io/"><img src="https://img.shields.io/static/v1?label=GenXD&message=Project&color=purple"></a> &ensp;
  <a href="https://arxiv.org/abs/2411.02319"><img src="https://img.shields.io/static/v1?label=Paper&message=Arxiv&color=red&logo=arxiv"></a> &ensp;
  <a href="https://huggingface.co/datasets/Yuyang-z/CamVid-30K"><img src="https://img.shields.io/static/v1?label=CamVid-30K&message=HuggingFace&color=yellow"></a> &ensp;
</div>



## Model Details

<p align="center" border-raduis="10px">
  <img src="https://gen-x-d.github.io/materials/figures/diffusion-model.png" width="80%" alt="teaser_page1"/>
</p>

### Model Description
GenXD leverages mask latent conditioned diffusion model to generate 3D and 4D samples with both camera and image conditions. In addition, multiview-temporal modules together with alpha-fusing are proposed to effectively disentangle and fuse multiview and temporal information.

- **Developed by:** NUS, Microsoft
- **Model type:** image-to-3D diffusion model, image-to-video diffusion model, image-to-4D diffusion model
- **License:** Apache-2.0

### Model Sources

- **Project Page:** https://gen-x-d.github.io
- **Repository:** https://github.com/HeliosZhao/GenXD
- **Paper:** https://arxiv.org/abs/2411.02319
- **Data:** https://huggingface.co/datasets/Yuyang-z/CamVid-30K


## Uses

### Direct Use

The model is intended for research purposes only. Possible research areas and tasks include

- Generation of artworks and use in design and other artistic processes.
- Applications in educational or creative tools.
- Research on generative models.
- Safe deployment of models which have the potential to generate harmful content.

- Probing and understanding the limitations and biases of generative models.

Excluded uses are described below.

### Out-of-Scope Use

The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model.

## Limitations and Bias

### Limitations

- The model does not achieve perfect photorealism.
- The model does not achieve perfect 3D consistency.

### Bias
While the capabilities of generation model is impressive, it can also reinforce or exacerbate social biases.