Skip to content
ModelListedExternal
Browse files

MiniMax H3 INT8 CONVROT

minimax-h3-community-license-agreement

Sourcehuggingface.co/Gluttony10/MiniMax-H3-INT8-CONVROT/tree/98759402b412b7d0ba9b636dbc6f14ddf1913957
KindModelBase modelMiniMaxAI/MiniMax-H3VersionMinimax h3 fl2v turbo 4step v0.1

Model source

Kind
Model
File size
577 MB–31.6 GB
Base model
MiniMaxAI/MiniMax-H3
Version
vMinimax h3 fl2v turbo 4step v0.1
Updated
Oct 18, 2026
Source
Hugging Face

Source description

MiniMax-H3 INT8 ConvRot

简体中文

Converted MiniMax-H3 weights for ComfyUI-RH-MiniMax-H3. This repository is a complete ComfyUI bundle: INT8 ConvRot DiT / text-encoder weights, merged VAEs, FL2VA / Ref2VA configs, and optional turbo LoRAs.

The same package is mirrored on ModelScope. Download from one source. The full snapshot is about 99 GiB; keep at least 120 GiB free.

Contents

FileSizeRole
MiniMax-H3-FL2VA-int8_convrot.safetensors31.65 GiBFL2VA / T2VA / V2A DiT
MiniMax-H3-Ref2VA-int8_convrot.safetensors31.65 GiBRef2VA DiT
qwen3-vl-32b-int8_convrot.safetensors25.28 GiBQwen3-VL text encoder
MiniMax-H3-video_vae.safetensors4.85 GiBVideo VAE
MiniMax-H3-audio_vae.safetensors0.56 GiBAudio VAE
minimax_h3_fl2v_turbo_4step_v0.1.safetensors1.29 GiBOptional FL2VA / T2VA 4-step turbo
minimax_h3_fl2v_turbo_4step_v1.0_768p_bf16.safetensors1.29 GiBOptional FL2VA / T2VA 4-step turbo for 768p
minimax_h3_fl2v_turbo_8step_v1.0_bf16.safetensors1.29 GiBOptional FL2VA / T2VA 8-step turbo
minimax_h3_ref2v_turbo_4step_v0.1_bf16.safetensors1.29 GiBOptional Ref2VA 4-step turbo
FL2VA/configsFL2VA tokenizer, processor, and component configs
Ref2VA/configsRef2VA tokenizer, processor, and component configs

Install into ComfyUI

ComfyUI/
└── models/
    └── MiniMax-H3-INT8-CONVROT/
        ├── MiniMax-H3-FL2VA-int8_convrot.safetensors
        ├── MiniMax-H3-Ref2VA-int8_convrot.safetensors
        ├── qwen3-vl-32b-int8_convrot.safetensors
        ├── MiniMax-H3-video_vae.safetensors
        ├── MiniMax-H3-audio_vae.safetensors
        ├── minimax_h3_fl2v_turbo_4step_v0.1.safetensors
        ├── minimax_h3_fl2v_turbo_4step_v1.0_768p_bf16.safetensors
        ├── minimax_h3_fl2v_turbo_8step_v1.0_bf16.safetensors
        ├── minimax_h3_ref2v_turbo_4step_v0.1_bf16.safetensors
        ├── FL2VA/
        └── Ref2VA/

cd /path/to/ComfyUI
python3 -m pip install -U huggingface_hub
hf download Gluttony10/MiniMax-H3-INT8-CONVROT \
  --local-dir ./models/MiniMax-H3-INT8-CONVROT

China users can use the ModelScope mirror:

cd /path/to/ComfyUI
python3 -m pip install -U modelscope
modelscope download --model Gluttony10/MiniMax-H3-INT8-CONVROT \
  --local_dir ./models/MiniMax-H3-INT8-CONVROT

Re-run the same command to resume or update an interrupted download. On a high-bandwidth machine with at least 64 GiB RAM, prefix hf download with HF_XET_HIGH_PERFORMANCE=1.

The plugin auto-detects this complete converted bundle. The legacy ComfyUI/models/MiniMax-H3 directory remains supported.

Optional Turbo LoRA

Select one turbo LoRA in the model loader for fewer sampling steps. Leave the LoRA empty to run the base converted weights.

FileTypical use
minimax_h3_fl2v_turbo_4step_v0.1.safetensorsFL2VA / T2VA 4-step turbo
minimax_h3_fl2v_turbo_4step_v1.0_768p_bf16.safetensorsFL2VA / T2VA 4-step turbo for 768p
minimax_h3_fl2v_turbo_8step_v1.0_bf16.safetensorsFL2VA / T2VA 8-step turbo
minimax_h3_ref2v_turbo_4step_v0.1_bf16.safetensorsRef2VA 4-step turbo

Plugin

Install ComfyUI-RH-MiniMax-H3 and use the nodes under RunningHub/MiniMax H3:

NodePurpose
RHMiniMaxH3ModelLoaderLoad the FL2VA / Ref2VA DiT and optional LoRA
RHMiniMaxH3TextEncoderLoaderLoad the Qwen3-VL text encoder
RHMiniMaxH3VAELoaderLoad the video and audio VAEs
RHMiniMaxH3VideoGenT2VA / FL2VA / V2A
RHMiniMaxH3RefGenRef2VA with ordered image, video, and audio references

Example workflows:

License

Converted weights follow the upstream MiniMax-H3 Community License. The ComfyUI plugin code is Apache-2.0.

Links

Sources

1 source
Hugging FacePrimaryVersion 98759402b412b7d0ba9b636dbc6f14ddf1913957
huggingface.co/Gluttony10/MiniMax-H3-INT8-CONVROT/tree/98759402b412b7d0ba9b636dbc6f14ddf1913957

Verified Oct 18

Download files

Model artifacts

9 artifacts

minimax_h3_fl2v_turbo_4step_v0.1.safetensors

safetensors · 1.29 GB · SHA-256 5ff4a12c8b45…5b29 · Hugging Face

Download file

minimax_h3_fl2v_turbo_4step_v1.0_768p_bf16.safetensors

safetensors · 1.29 GB · SHA-256 1bdabc2e9fce…416c · Hugging Face

Download file

minimax_h3_fl2v_turbo_8step_v1.0_bf16.safetensors

safetensors · 1.29 GB · SHA-256 e16ac20824d6…807f · Hugging Face

Download file

minimax_h3_ref2v_turbo_4step_v0.1_bf16.safetensors

safetensors · 1.29 GB · SHA-256 9e642fc8749c…ae99 · Hugging Face

Download file

MiniMax-H3-audio_vae.safetensors

safetensors · 577 MB · SHA-256 37dddc2f3e6d…5ea2 · Hugging Face

Download file

MiniMax-H3-FL2VA-int8_convrot.safetensors

safetensors · 31.6 GB · SHA-256 4e464ae3d21f…f738 · Hugging Face

Download file

MiniMax-H3-Ref2VA-int8_convrot.safetensors

safetensors · 31.6 GB · SHA-256 f7ed6f021b08…be8a · Hugging Face

Download file

MiniMax-H3-video_vae.safetensors

safetensors · 4.85 GB · SHA-256 aa4a9ffb89cc…bbfa · Hugging Face

Download file

qwen3-vl-32b-int8_convrot.safetensors

safetensors · 25.3 GB · SHA-256 e9d0a5cc9df0…3203 · Hugging Face

Download file

Source excerpts

2 excerpts
ReadmeOct 18huggingface.co/Gluttony10/MiniMax-H3-INT8-CONVROT

--- license: other license_name: minimax-h3-community-license-agreement license_link: https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE library_name: comfyui base_model: MiniMaxAI/MiniMax-H3 pipeline_tag: image-text-to-video tags: - comfyui - text-to-video - image-to-video - audio-video-generation - multimodal - int8 --- # MiniMax-H3 INT8 ConvRot [简体中文](README_CN.md) Converted MiniMax-H3 weights for [ComfyUI-RH-MiniMax-H3](https://github.com/RH-RunningHub/ComfyUI-RH-MiniMax-H3). This repository is a complete ComfyUI bundle: INT8 ConvRot DiT / text-encoder weights, merged VAEs, FL2VA / Ref2VA configs, and optional turbo LoRAs. The same package is mirrored on [ModelScope](https://modelscope.cn/models/Gluttony10/MiniMax-H3-INT8-CONVROT). Download from **one** source. The full snapshot is about **99 GiB**; keep at least **120 GiB** free. ## Contents | File | Size | Role | |---|---:|---| | `MiniMax-H3-FL2VA-int8_convrot.safetensors` | 31.65 GiB | FL2VA / T2VA / V2A DiT | | `MiniMax-H3-Ref2VA-int8_convrot.safetensors` | 31.65 GiB | Ref2VA DiT | | `qwen3-vl-32b-int8_convrot.safetensors` | 25.28 GiB | Qwen3-VL text encoder | | `MiniMax-H3-video_vae.safetensors` | 4.85 GiB | Video VAE | | `MiniMax-H3-audio_vae.safetensors` | 0.56 GiB | Audio VAE | | `minimax_h3_fl2v_turbo_4step_v0.1.safetensors` | 1.29 GiB | Optional FL2VA / T2VA 4-step turbo | | `minimax_h3_fl2v_turbo_4step_v1.0_768p_bf16.safetensors` | 1.29 GiB | Optional FL2VA / T2VA 4-step turbo for 768p | | `minimax_h3_fl2v_turbo_8step_v1.0_bf16.safetensors` | 1.29 GiB | Optional FL2VA / T2VA 8-step turbo | | `minimax_h3_ref2v_turbo_4step_v0.1_bf16.safetensors` | 1.29 GiB | Optional Ref2VA 4-step turbo | | `FL2VA/` | configs | FL2VA tokenizer, processor, and component configs | | `Ref2VA/` | configs | Ref2VA tokenizer, processor, and component configs | ## Install into ComfyUI ```text ComfyUI/ └── models/ └── MiniMax-H3-INT8-CONVROT/ ├── MiniMax-H3-FL2VA-int8_convrot.safetensors ├── MiniMax-H3-Ref2VA-int8_convrot.safetensors ├── qwen3-vl-32b-int8_convrot.safetensors ├── MiniMax-H3-video_vae.safetensors ├── MiniMax-H3-audio_vae.safetensors ├── minimax_h3_fl2v_turbo_4step_v0.1.safetensors ├── minimax_h3_fl2v_turbo_4step_v1.0_768p_bf16.safetensors ├── minimax_h3_fl2v_turbo_8step_v1.0_bf16.safetensors ├── minimax_h3_ref2v_turbo_4step_v0.1_bf16.safetensors ├── FL2VA/ └── Ref2V...

NoteOct 18huggingface.co/Gluttony10/MiniMax-H3-INT8-CONVROT

Source context: 0 downloads · 21 likes · Pipeline image-text-to-video · Library comfyui · Repo Gluttony10/MiniMax-H3-INT8-CONVROT