Rex-Omni
This model is Rex-Omni, a 3B-parameter Multimodal Large Language Model (MLLM) presented in the paper "Detect Anything via Next Point Prediction".
text + image → text · made by IDEA-Research
Sold by
Nobody in the catalogue publishes a price for this yet.
About
Rex-Omni — a text model from IDEA-Research.
It takes text and images and returns text. It was published in October 2025. The catalogue files it under chat. Its weights are published under the other licence, which attaches conditions the plain open licences do not.
Every current figure
- Maker
- IDEA-Research
- Register
- model
- Takes
- text + image
- Returns
- text
- Published
- October 2025
- Parameters
- 4.1 billion · read from its own weights
- Licence
- other
Known as 1 name
IDEA-Research/Rex-Omni