Hacktoberfest 2026：メンテナが10月に向けて印を付けた、オープンで初心者向けの issue。 Hacktoberfest の issue を見る

MiniMax H3 Ref2VA: Significant Reference-Fidelity Regression in Local ComfyUI

オープン
  • 何か問題がありますか？
#84 コメント 0 件 リアクション 0 件 担当者 0 名 GitHub で見る

まだ誰も着手していません。

評価

難易度
5/5
見積もり時間
1週間以上
初心者へのやさしさ
35/100
issue の種類
バグ
明瞭さ
説明が足りない
活発さ
活発
技術スタック
python, pytorch
領域
ai, machine-learning

調査の方向性

Start by reproducing the local H3 Ref2VA workflow on ComfyUI v0.37.2 and compare its output with the older setup and RunningHub result. Investigate where fidelity diverges during TAEH3 sampling, including reference conditioning, ModelSamplingAV, runtime precision, and the --fast fp16_accumulation setting; use the related ComfyUI issue #16589 for comparison. Done means isolating a reproducible execution-path or configuration cause and documenting the affected component.

索引モデルが issue の本文から書いたものです。

説明

Description

I’m experiencing a significant reference-fidelity issue with MiniMax H3 Ref2VA in my local ComfyUI setup.

The model is expected to preserve the major visual identity and spatial structure of the reference image while animating it. However, in my current local setup, major elements of the reference can be substantially reinterpreted or changed.

Examples include:

  • Object geometry and proportions changing
  • Fabric folds and clothing structure being altered
  • Frame/box geometry changing
  • Background structures being reinterpreted
  • Overall composition drifting from the reference
  • Important visual details being regenerated rather than preserved

This is not simply a minor temporal inconsistency. The generated result can differ substantially from the original reference structure.

Important comparison

I have an older local setup where the same general workflow and the same model files produced substantially better reference fidelity.

I also get substantially better reference adherence when running the same general H3 Ref2VA workflow through RunningHub.

This suggests that the problem may be related to the local ComfyUI/runtime/inference path rather than the model weights themselves.

Where the divergence appears

An important observation is that the reference fidelity appears to diverge during TAEH3 sampling, before the final video VAE decoding stage.

Therefore, this does not appear to be only a video-VAE decoding or rendering issue.

Environment

  • GPU: NVIDIA RTX 4070 SUPER 12 GB
  • RAM: 32 GB
  • CPU: Intel Core i5-14600K
  • ComfyUI: v0.37.2
  • Windows
  • Local H3 Ref2VA workflow

Model files:

  • "minimax_h3_Singularity_ref2va_Pruned_v1.3_int8.safetensors"
  • "minimax_h3_video_vae_int8_convrot.safetensors"
  • "minimax_h3_audio_vae_fp32.safetensors"
  • "qwen3vl_32b_minimax_h3_nvfp4_awq_2.safetensors"

Related observation: fp16 accumulation

Another H3 user reported that removing the "--fast fp16_accumulation" startup flag and ensuring that no custom nodes enabled fp16 accumulation made reference adherence substantially better.

I have not established that this is the root cause of my specific issue, but it may be worth investigating because numerical precision or attention/runtime settings could potentially affect reference conditioning.

Possible areas to investigate

Could you please check whether recent changes or runtime differences can affect:

  1. Ref2VA reference conditioning
  2. Reference-latent injection
  3. Qwen3-VL image/reference encoding
  4. Reference image preprocessing and "ref_image_size"
  5. TAEH3 sampling
  6. Sampler/scheduler or sigma-shift behavior
  7. "ModelSamplingAV"
  8. OUTER_SAMPLE wrappers or other model patches
  9. Attention backend/runtime differences
  10. INT8/NVFP4 execution and numerical precision
  11. "torch.backends.cuda.matmul.allow_fp16_accumulation"
  12. Recent ComfyUI changes affecting the H3 Ref2VA execution path

Related ComfyUI investigation

I have documented the local ComfyUI investigation here:

https://github.com/Comfy-Org/ComfyUI/issues/16589

There is also another user reporting similar H3 reference-adherence degradation in that discussion.

Expected behavior

The major visual identity, geometry, proportions, spatial relationships, and important structures of the reference image should remain substantially consistent while the model performs the requested animation.

Actual behavior

The reference is being substantially reinterpreted during generation, with major structures and visual details changing even though the same general workflow and model files previously produced much stronger reference adherence.

Any guidance on which component or recent change could cause this behavior would be greatly appreciated.

主要言語
Python
スター
9.8k
フォーク
738
30日以内にマージされた PR はありません

環境構築

このプロジェクトには開発コンテナ、Dockerfile、コントリビューションガイドがありません。まず README を読み、一般的な手順ははじめてのコントリビューションガイドを参照してください。

はじめの一歩

  1. issue を最後まで読み、次にプロジェクトのコントリビューションガイドを読みます。
  2. 着手することを issue にコメントします — 二人が同じ作業をするのを防げます。
  3. リポジトリをフォークし、ブランチを切って変更します。
  4. issue 番号を参照したプルリクエストを送ります。

MiniMax-AI/MiniMax-H3 のほかの issue

MiniMax-AI/MiniMax-H3 の issue をすべて見る

似ている issue

Python の issue をもっと見る

新しい issue をメールで受け取る

初心者向けの GitHub issue を短くまとめたダイジェスト。