---
title: TRELLIS-image-large
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/TRELLIS-image-large"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/TRELLIS-image-large.md"
repository: AI-ModelScope/TRELLIS-image-large
last_updated: 2024-12-08
license: mit
pipeline_tag: image-to-3D
tasks:
  - image-to-3D
parameters: 1.6B
tensor_type:
  - F32
  - F16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 8455
stars: 2
---

# TRELLIS-image-large

> TRELLIS-image-large - AI-ModelScope 在 ModelScope 开源的模型。The image conditioned version of TRELLIS, a large 3D genetive model. It was introduced in the paper Structured 3D Latents for Scalable and Versatile 3D Generation.

AI-ModelScope/TRELLIS-image-large 是 ModelScope 魔搭社区上的 1.6B 参数image-to-3D模型，采用 mit 许可。

- **Repository**: AI-ModelScope/TRELLIS-image-large
- **License**: mit
- **Tasks**: image-to-3D
- **Parameters**: 1.6B
- **Downloads**: 8455
- **Stars**: 2
- **Last updated**: 2024-12-08

Source: https://www.modelscope.cn/models/AI-ModelScope/TRELLIS-image-large

---

# TRELLIS Image Large

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

The image conditioned version of TRELLIS, a large 3D genetive model. It was introduced in the paper [Structured 3D Latents for Scalable and Versatile 3D Generation](https://huggingface.co/papers/2412.01506).

Project page: https://trellis3d.github.io/

Code: https://github.com/Microsoft/TRELLIS