showlab/Show-o

[ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.

47
/ 100
Emerging

This project offers a single AI model capable of understanding and generating content across various formats like text, images, and videos. It takes mixed inputs, such as text descriptions, images, or video clips, and can produce new images, videos, or detailed textual explanations and answers. It is designed for AI researchers and machine learning engineers working on advanced multimodal AI systems.

1,894 stars.

Use this if you are developing or experimenting with unified AI models that can process and create content across text, image, and video modalities simultaneously.

Not ideal if you need a simple tool for basic image editing, video playback, or text translation without requiring complex multimodal understanding or generation capabilities.

multimodal-ai generative-models computer-vision natural-language-processing deep-learning-research
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

1,894

Forks

89

Language

Python

License

Apache-2.0

Last pushed

Jan 08, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/showlab/Show-o"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.