Nodes/MiniMax H3 Power LoRA Stack/MiniMax H3 Power LoRA Stack
ComfyUI Node

MiniMax H3 Power LoRA Stack

Stacked multi-LoRA loader for MiniMax H3 across every weight format. Handles the three things the stock loader and rgthree's Power Lora Loader get wrong on H3: * quantized bases -- w4a8/int4 weights are patched with an exact runtime branch instead of a lossy dequantize/requantize merge; * adaLN basis mismatch -- LoRAs trained against a dense checkpoint are rebased onto a pruned checkpoint's curve, instead of being skipped; * key conventions -- ai-toolkit, kohya, lycoris, peft and bare-prefix layouts all resolve against the model's own key set.

By cicalooo·Created 2 months ago·Updated 15 days ago· 7
MiniMax H3 Power LoRA Stack
  • model
  • adaln_modality
  • schedule
  • MODEL
  • report
◄quantized_layersauto►
◄adaln_portauto►
CategoryMiniMax-H3/lora

Inputs (5)

NameTypeDefaultDescription
modeloptMODEL—
quantized_layersoptCOMBOautoauto: runtime branch for quantized layers, merge for the rest. branch: never modify a weight. merge: stock behaviour (destroys LoRAs on w4a8/int4).
adaln_portoptCOMBOautoRebase adaLN LoRA pairs between dense (2688) and curve (8) checkpoints. Needs h3_silu_temb_grid.safetensors.
adaln_modalityoptH3_MODALITYOptional. Wire a MiniMax H3 adaLN Modality node here to scale every stacked LoRA's adaLN modulation per modality.
scheduleoptH3_SCHEDULEOptional. Wire an H3 LoRA Schedule chain here to vary selected row strengths over the denoising trajectory.

Outputs (2)

NameTypeDescription
MODELMODELPatched model
reportSTRINGPer-LoRA account of what was applied