CivArchive
    Minimax-LowVRAM - TURBIA
    NSFW

    šŸŽžļø this is a place for Minimax H3 Video workflows that are working in low-VRAM GPUs

    Turbo LORA / Nodes from: https://huggingface.co/larryvrh/MiniMax-H3-Turbo-Lora
    or Lightx2v LORA: https://huggingface.co/lightx2v/Minimax-h3-Turbo/tree/main
    Audio VAE from: https://huggingface.co/dummy9996/minimax_h3_vae_fp8/tree/main
    Video VAE from: https://huggingface.co/Kijai/MiniMax-H3-experimental/tree/main
    Uncensored TE from: https://huggingface.co/ethanfel/Qwen3-VL-32B-Ultra-Heretic-H3-ComfyUI-INT8-ConvRot/tree/main

    Also you can Download Resources from any of these repos:
    https://huggingface.co/tsolful/Minimax_H3_INT4MixedConvRot/tree/main
    https://huggingface.co/Abiray/Minimax-H3-nvfp4-INT4-INT8-Convrot/tree/main
    https://huggingface.co/Merserk/MiniMax-H3-INT4-ConvRot/tree/main
    and ...
    Official ComfyUI Minimax H3: https://huggingface.co/Comfy-Org/MiniMax-H3/tree/main

    For live previews node get: https://huggingface.co/Kijai/MiniMax-H3-TAE

    P.S.: you should learn how to use this model framework - it is really worth your tears and wasted hours of trial/errors ;)

    Description

    faster gens without attention / sampler tricks

    FAQ

    Comments (11)

    TTTTT55Aug 6, 2026Ā· 1 reaction
    CivitAI

    How fast? On what hardware?

    0l1v1aR0551
    Author
    Aug 6, 2026Ā· 2 reactions

    speed depends on steps + video duration, hardware < 12 GB Vram

    TTTTT55Aug 6, 2026Ā· 1 reaction

    @0l1v1aR0551Ā I see, thanks

    SantodanAug 8, 2026

    @0l1v1aR0551Ā ok, but in your low VRAM hardware, what was the speed and the hardware?

    0l1v1aR0551
    Author
    Aug 8, 2026Ā· 2 reactions

    @SantodanĀ 7 sec video - 22 min at 4 steps

    Mikel007Aug 17, 2026

    NVIDIA GeForce RTX4080 with 12 GB VRAM and 32 GByte normal RAM 30 minutes for a 10 seconds video with sound (idealia, 8Steps)

    0l1v1aR0551
    Author
    Aug 17, 2026

    @Mikel007Ā there is a possible reason for that - the kj node that feeds junks of model forward slows generation down / preventing VRAM overflow...
    also some Comfyui settings like commandline --low-vram do the same effect - so, by optimizing your memory management you should have way faster gens of short vids (10-15 secs) on such nice hardware as you just mention!

    jvollmerlcpc840Aug 6, 2026Ā· 1 reaction
    CivitAI

    Node 'ID #136' has no class_type. The workflow may be corrupted or a custom node is missing.: Node ID '#136'

    0l1v1aR0551
    Author
    Aug 6, 2026

    update Comfy to the nightly (not stable) version for this to work!

    wangyone91766Aug 7, 2026Ā· 1 reaction
    CivitAI

    Thank you very much for your work. However, with my 6GB+16GB laptop, I have tried all the Minimax low-VRAM version workflows and encountered an error with every one of them:

    Error message: # ComfyUI Error Report ## Error Details - Node ID: 129 - Node Type: VAEDecode - Exception Type: RuntimeError - Exception Message: RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument tensors in method wrapper_CUDA_cat)

    I hope someone kind can help me figure out why I get an error every time the process reaches VAE video decoding.

    0l1v1aR0551
    Author
    Aug 7, 2026

    go for INT4 safetensors wherever you can - look in all links of repos provided in this WF card - scan them regularly for new and / old INT convrot ones and test them on you computer = this is for low vram / ram issues;

    but also - set Comfyui to nightly version !!! and update it several times a day ;)

    Workflows
    MiniMax H3

    Details

    Downloads
    287
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/6/2026
    Updated
    9/19/2026
    Deleted
    -

    Files

    minimaxLowvram_turbia.zip

    Mirrors

    CivitAI (1 mirrors)