Add minimax_h3 to IMG_ARCH_LIST - #476
Open
GabrielSalerno03 wants to merge 1 commit into
Open
Conversation
GabrielSalerno03
force-pushed
the
fix/minimax-h3-arch
branch
from
August 20, 2026 06:17
e9cc598 to
d321e22
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
MiniMax H3 UNet GGUFs that set
general.architecture = "minimax_h3"are rejected by the loader:ComfyUI has native H3 support (
comfy/ldm/minimax/,comfy_extras/nodes_minimax_h3.py), and the Qwen3-VL text encoder already loads becauseqwen3vlis inTXT_ARCH_LIST— only the diffusion model side is blocked.Of the two community repacks I tested,
minimax_h3_fl2va_pruned_fp8_Q4_0.ggufdeclaresminimax_h3and fails, whileMiniMax-H3-FL2VA-Q3_K_M.ggufdeclareswanand loads. So at present the list only accepts H3 files that are mislabeled.Tested on ComfyUI 0.33.0 with the pruned fp8 Q4_0 repack; text-to-video and image-to-video both generate correctly with this change.