Nodes/ComfyUI-NynxzH3/H3 Depth Skip
ComfyUI Node

H3 Depth Skip

Skips named transformer blocks, or just their attention half. Use MiniMax H3 Block Contribution first to find out which blocks are idle on your model — on the released checkpoints that is roughly 3-17, worth about 1.4x. Empty is an exact no-op.

By Nynxz·Created 14 days ago·Updated 5 days ago· 4
H3 Depth Skip
  • model
  • MODEL
  • report
blocks
start_percent0.00
end_percent1.00
modeattention_only
CategoryNynxz/H3/Sampling

Inputs (5)

NameTypeDefaultDescription
modelMODELA MiniMax H3 model.
blocksSTRINGBlock indices to skip: '3-17', '3-17, 22', '10'. Ranges are inclusive. Empty changes nothing. Read them off MiniMax H3 Block Contribution rather than guessing — the quiet band is a property of the checkpoint, and it is identical across the fl2va and ref2va releases.
start_percentFLOAT0.000–1Where in the schedule the skip switches ON, as a fraction of sampling. 0 is the first step.
end_percentFLOAT1.000–1Where it switches OFF. 1 runs to the last step; the default pair (0, 1) is always-on, which is the behaviour this node had before. Ending early is the useful setting: skip the quiet band while structure is being decided, then run the full stack for refinement, where the blocks you dropped may matter more than their average contribution suggests.
modeCOMBOattention_onlyattention_only keeps the MLP, which is the conservative choice and costs about a fifth of the saving — attention is ~83% of block time at these sequence lengths. It is also the better-evidenced one: the MLP's gate varies 8x across depth against attention's 68x, so the MLP is much less obviously idle in any band. whole_block drops everything and is the thing to reach for once an A/B says the band really is inert.

Outputs (2)

NameTypeDescription
MODELMODEL
reportSTRINGWhich blocks were skipped, what fraction of the forward that removes, and what the number does and does not mean.