Skip to content
Other

MiniMax H3 ComfyUI

репак файлов, квантов и LoRA для видео

1 min read

Репозиторий fkyyy/MiniMax-H3-comfy-r2v-slim — это переупакованные файлы MiniMax H3 для ComfyUI. Внутри диффузионные модели, текстовые энкодеры Qwen3-VL-32B, VAE, LoRA, ControlNet и эмбеддинги для генерации видео. Число параметров и архитектурные детали самой MiniMax H3 в карточке не указаны.

Ключевые особенности

  • Diffusion-модели в вариантах bf16, int8_convrot, pruned, w6a8 и fp8_scaled.
  • Текстовые энкодеры Qwen3-VL-32B, видео- и аудио-VAE, LoRA Turbo на 4/8 шагов и ControlNet Union.
  • Энкодер nvfp4_awq не требует GPU Blackwell.
  • Для diffusion-моделей рекомендуется int8_convrot при PyTorch с cu130; fp8_scaled — только если int8_convrot недоступен.
  • В карточке есть workflow для text-to-video, image-to-video, reference-to-video, continuation, multiframe reference и Fun ControlNet Union.
  • 10 эмбеддингов для эффектов: art_is_explosion, blooming_flowers, bullet_time, dark_magic, fire_breath, four_seasons, kiss_camera, spiral_ascent, storm_magic, truman_show.

Пример

Вызов эмбеддинга в промпте для CLIPTextEncode:

embedding:minimaxh3_art_is_explosion
ПодробнееПодробнее
Бенчмарки и требования к VRAM в карточке не указаны.
nvfp4-энкодер не требует Blackwell; для diffusion предпочтителен int8_convrot при PyTorch cu130.
fp8_scaled — запасной вариант, если int8_convrot недоступен.
Есть отдельные workflow для i2v, r2v, t2v, continuation, multiframe reference и Fun ControlNet Union.
Оригинальные репозитории: MiniMaxAI, lightx2v, alibaba-pai и Kijai.
Примеры
Discuss Telegram 0 121

Will it run?

Only with RAM offload

Even 4-bit is larger than your VRAM. Some layers can stay in system RAM (llama.cpp, ComfyUI), but it will be several times slower.

  • INT8recommendedweights 39 GB · ready files43 GB
  • 4-bitweights 22 GB25 GB

Tip: go 8-bit.INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: Won't fit any home GPU — renting is cheaper.

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # fkyyy/MiniMax-H3-comfy-r2v-slim
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download fkyyy/MiniMax-H3-comfy-r2v-slim --local-dir ~/models/MiniMax-H3-comfy-r2v-slim
    # The model is in ~/models. How to run it is in the model card (link above).
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

MiniMax H3 prompts

All prompts

Ready prompts with the resulting video: copy and try.

Model family

New posts about versions of MiniMax-H3 (quants, finetunes, LoRAs) will show up under the bell.

Quantised versions 12All on Hugging Face
Fine-tunes 12All on Hugging Face
LoRAs and adapters 12All on Hugging Face
Merges 3All on Hugging Face

About the model

fkyyy/MiniMax-H3-comfy-r2v-slim
Author
fkyyy
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

1210

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments