Model Card for EpiDiff

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.

Model Details

Model Description

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

Model Sources

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

Uses

For usage instructions, please refer to our EpiDiff GitHub repository.

Training Details

Training Data

We use renders from the LVIS dataset, utilizing huanngzh/render-toolbox.