inclusionAI/Ming-UniVision

Code release for Ming-UniVision: Joint Image Understanding and Geneation with a Continuous Unified Tokenizer

34
/ 100
Emerging

This project helps creative professionals and researchers who work with both images and text by providing a way to seamlessly generate, understand, and edit visual content using natural language. You can input text prompts or existing images, and the system can produce new images, answer questions about images, or modify parts of an image through conversational interaction. It's for designers, content creators, or AI researchers exploring advanced multimodal capabilities.

142 stars. No commits in the last 6 months.

Use this if you need to create, interpret, or alter images in a continuous, conversational flow without converting between different formats or states.

Not ideal if your primary need is simple image classification, object detection, or if you require extremely fine-grained, pixel-level control not driven by high-level semantic instructions.

Generative AI Image Creation Visual Storytelling Content Editing Multimodal Research
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 7 / 25

How are scores calculated?

Stars

142

Forks

5

Language

Python

License

MIT

Last pushed

Oct 14, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/inclusionAI/Ming-UniVision"

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