adirik / mvdream

Generate 3D assets using text descriptions

  • Public
  • 966 runs
  • GitHub
  • Paper
  • License
Run with an API
Playground API Examples README Versions

Run time and cost

This model costs approximately $3.24 to run on Replicate, or 0 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 56 minutes.

Readme

MVDream

MVDream is a text-to-3D model that can generate 3D assets via score distillation on self-generated multi-views. See the original repository and paper for details. Note that this model is intended to generate singular objects and can not generate scenes.

How to use the API

To use MVDream, simply enter a text description of the 3D asset you would like to generate. Training / generating a 3D asset takes about 55-60 minutes. The API input arguments are as follows:

  • prompt: text prompt to generate 3D asset from.
  • negative_prompt: text prompt to describe attributes or features you don’t want in your 3D asset.
  • num_steps: number of training steps. Strongly advised to keep the default value for optimal results.
  • seed: seed for reproducibility, default value is None. Set to an arbitrary value for deterministic generation.

References

@article{shi2023MVDream,
  author = {Shi, Yichun and Wang, Peng and Ye, Jianglong and Mai, Long and Li, Kejie and Yang, Xiao},
  title = {MVDream: Multi-view Diffusion for 3D Generation},
  journal = {arXiv:2308.16512},
  year = {2023},
}