Appgithub-com-larryvrh-comfyui-minimax-h3-turbo

Download Pinokio

Sign in Create accountJoin

Sign in Create accountJoin

ComfyUI-MiniMax-H3-Turbo

github.com/larryvrh/comfyui-minimax-h3-turboUpdated 2mo ago

Contribute to Larryvrh/ComfyUI-MiniMax-H3-Turbo development by creating an account on GitHub.

Loading community details…

Loading project owner…

Loading launchers…

Loading check-ins…

Community

Sort byCreate post

Ask or share about ComfyUI-MiniMax-H3-Turbo…

Loading...

Loading references…

Loading project activity…

Pinokio

0

Projects using this repository

No references listed yet.

Check-ins (0)

Recent commits

Merge pull request #16 from afkaf/main

LarryVRH2 months ago4274783

Merge pull request #10 from bkunbargi/fix-audio-ref-adaln-rows

LarryVRH3 months ago546b502

README: v4-600 vs v1-850 decision tree — v1-850 is friendlier for 4-step heavy motion

developer3 months ago55fee86

README: overhaul — v4-600 is the current recommended checkpoint; clarify 4-8 step range

developer3 months ago2dcbf1b

v1.2.3: auto-adapt the sampler to ComfyUI's native ModelSamplingAV; fix skipped int8 fc2 LoRA

developer3 months ago77bfa67

v1.2.2: fix pruned-base unload crash + bypass VRAM regression (issue #4); add low_vram switch

developer3 months agoa7624b4

README: LoRA-strength tip for the sharpness/artifact trade-off (v1.2.1)

developer3 months ago55f85c6

Apply LoRA at run time (bypass) instead of merging; device-safe adaln; restore it/s progress bar; add forward observability (v1.2.0)

developer3 months agocc6eb25

README: ask users to keep the node updated

Larryvrh3 months ago96cc1dd

Pruned/curve base support: run-time adaln injection, one LoRA covers all bases (v1.1.0)

Larryvrh3 months agoe7ad532