CivArchive
    Minimax H3: t2va (T2V) – Polyhedron: Perfect Eyes // Perfect Skin // Perfect Hands - v1.0
    NSFW

    TL;DR: This LoRA helps with skin texture, the eyes and the hands for Minimax H3: t2va. It's the final LoRA model and might be already overtrained ... so use it with lower weights. Just experiment!

    Okay, folks,

     I don't really know what to say other than: MiniMax H3 is ridiculously good. <3 The hype is real. I've spent the last few days messing around with both models:

     
    ref2va (reference/image to video) [Get ready to meet your maker!]

    t2va (text to video) [here]

     

    So here's my first LoRA — the bread-and-butter one: skin, hands and eyes. And I hit a wall almost immediately. We need to be a bit careful with LoRAs here, because it's the same story as with Wan 2.2: the base model already knows(!) what all of this is supposed to look like, and that can clash. Anyway. They do have an effect, but the whole thing is very prompt-sensitive. Keep that in mind.

     
    The current videos were made with four LoRAs, two of mine, two external:

     
    *polyhedron_minimax_h3_image_lora_v2__nippl8es // (currently only up on my Patreon — we'll be needing this one later, wink wink)
    https://www.patreon.com/c/polyhedron_ai

     

    *polyhedron_minimax_h3_image_lora_v2__perfe8ct // (this is the LoRA here in its final version; if it feels overtrained to you, all the training steps are on my Patreon as well with the workflows I used for the example videos)

     
    And then two external ones. First:

     

    https://civarchive.com/models/2884206/minimax-h3-photorealistic-image-generator-lora-workflow?modelVersionId=3260165

     

    That's what got me started on this LoRA in the first place — though the workflow is an absolute mess. So I'm putting up a clean, tidied-up one that by now runs entirely on Polyhedron Suite nodes. The quality speaks for itself. Go try it. I've also gone and pulled the whole MiniMax H3 universe into my own repo, which you can grab here — updated today — and it's available through the ComfyUI Manager too:

     

    https://github.com/PolyhedronAI/ComfyUI-PolyhedronLoRAStack

     

    And here's the second LoRA:

     

    https://civarchive.com/models/2858760/minimax-h3-tiddies-and-realism-slider?modelVersionId=3229050

     

    Tiddies! Already in there, and we'll be needing that one later as well. :D

     

    We've been hearing "this model is the real gamechanger" for years now. This time I actually think it's true. :)

     

    Catch you later!

     

    Frank

    Description

    V1.0

    FAQ

    Comments (14)

    psspsspsspssspssAug 29, 2026· 17 reactions
    CivitAI

    Your description is long and describing a bunch of different other things. Your videos just show someone crying. What exactly does this lora do?

    JJoker375Aug 29, 2026· 1 reaction

    realistic skin and better eyes probably what bothers me is there is no recommended weight ( lora strength ) and settings in the description

    olivettyAug 29, 2026· 1 reaction

    @JJoker375 just experiment!

    kevinpawseyAug 30, 2026

    and what was meant by ref2va (get ready to meet your maker)? I am confused about that, I use it all the time for extending videos and it is amazing (if you get the prompting right).

    JJoker375Aug 30, 2026

    @olivetty is this the final version or you plan on mor realism loras cuz i think minimax right now needs more of these

    sarahbonestoneAug 30, 2026· 1 reaction

    She is crying because she is constipated.

    LuringSuccubusAug 30, 2026

    @sarahbonestone  I SEE

    kermitfrog1202Aug 30, 2026

    @JJoker375 MiniMax H3 Power LoRA Stack automatically puts the strength at 0.64....

    tta175Aug 29, 2026· 2 reactions
    CivitAI

    this lora helps a lot on low resolution, less artefacts, big thanks

    kenybob09431Aug 29, 2026· 1 reaction
    CivitAI

    thanks

    mankogamerhnAug 30, 2026· 2 reactions
    CivitAI

    Hello, I have a couple of questions. Do this lora works for Ref2VA or only T2VA? Which is the suggested weight to use? Did you train it with Turbo Loras or also with the base Minimax Version?

    Polyhedron_AI
    Author
    Aug 30, 2026· 1 reaction

    Hi there: I guess, it's only trained with the T2VA-Model (with Ostris on runpod) because only still images were used - but maybe it has also an effect on Ref2VA? No Turbo LoRAs were involved ... I use a weight of 0.4-0.6, but test it for yourself ... :) Have fun! Frank

    mankogamerhnAug 30, 2026

    @Polyhedron_AI Thank you very much for your reply. I will test it right now. I hope everything comes fine

    Polyhedron_AI
    Author
    Aug 30, 2026· 1 reaction

    @mankogamerhn Yes. I am also testing, especially Sampler/Scheduler-combinations like "res_multistep" with "Simple" with no Turbo ... Keep it up. :)

    LORA
    MiniMax H3

    Details

    Downloads
    1,107
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/29/2026
    Updated
    9/1/2026
    Deleted
    -
    Trigger Words:
    perfe8ct
    perfect hands
    perfect skin
    perfect eyes

    Files

    polyhedron_minimax_h3_image_lora_v2__perfe8ct.safetensors