MiniMax Livestream Reveals Plans to Open-Source Unified T2I and Editing Model

bdsqlsz · x · 2026-08-08

According to a recent tweet, MiniMax announced during a livestream its plans to open-source a unified image model for text-to-image (T2I) and editing. The upcoming model will reportedly utilize the same VAE as the H3 model.

Original post →

More from Multimodal

Multimodal channel →