manateelazycat/MiniMax-H3-Image-AIPod

MiniMax-H3-Image for AI Pod

Powered by MiniMax-H3-Image. Read the complete upstream license, territorial and use restrictions, and NOTICE before use. This release uses SGLang Diffusion's native MiniMax-H3-Image pipeline, explicitly selecting --backend sglang. It does not use a standalone PyTorch/Diffusers model implementation or automatic backend fallback. The model directory retains the original immutable upstream checkpoint layout and separate H3 BF16 text encoder. Only completed fixed-revision release manifests and their final LPK are installation inputs.