CivArchive
    MiniMax H3 Image: Seed Hunter + medium picker (ComfyUI) - v2.0
    NSFW
    Preview 143588399
    Preview 143586902
    Preview 143588404
    Preview 143586900
    Preview 143586906
    Preview 143586907
    Preview 143586910
    Preview 143586933
    Preview 143586932

    Seed hunting workflow for MiniMax-H3-Image. Hunt seeds at 4 MP, pick one, render it at 16 MP. Native ComfyUI nodes only, no custom packs.

    Why a hunt at 4 MP and not "same seed, bigger size"

    • In H3-Image a seed does not keep its picture when the size changes. Seed 42 at 4 MP and seed 42 at 16 MP are two different photos.

    • So the final stage takes your pick as <Picture 1> plus your full prompt and renders it at 16 MP. Composition, people and text carry over, the 16 MP pass adds the detail.

    • The full prompt also fixes small things the pick got wrong, as long as the prompt describes them.

    The medium picker

    • Without a stated medium, H3-Image goes for a crunchy, over-sharpened HDR look, worst on faces. MiniMax's own demo Space does the same with a bare prompt.

    • The dropdown puts a tested medium sentence in front of your scene: 35mm film, full-frame digital, phone selfie, phone main camera, or none.

    • Film gives the most natural skin. The phone options make convincing UGC stills. Pick none for illustrations, posters and studio product shots and name the medium yourself.

    • In the gallery: same seed, same scene, with and without the medium, 100% crop.

    How to use

    1. Pick a medium, write the scene. Visible text in double quotes. No skin or sharpness words (pores, 8k, hyper-detailed).

    2. Pick the aspect ratio. Final is 16 MP, the hunt runs at 4 MP.

    3. Set the number next to Run to 4 and press Run. Seed is on increment, so you get 4 seeds, saved as hunt_s<seed>.

    4. Type the seed you like into seed, set it to fixed, click the 4 · FINAL group title, Ctrl+M to switch it on, Run once.

    5. Next hunt: Ctrl+M on 4 · FINAL to switch it off, seed back to increment.

    The model renders one image at a time (batch size 1), so the hunt is a queue of single runs, not a batch.

    Speed, RTX PRO 4500 (32 GB) with 57 GB system RAM: about 6.5 s per 4 MP hunt seed, about 75 s per 16 MP final. ComfyUI streams the 21 GB model from system RAM, so a 32 GB card runs the full int8 model.

    Mac: one ComfyUI process can't hold the 21 GB model and the 25 GB text encoder on a 48 GB Mac. Untested on 64 GB and up.

    Models, from Hugging Face Comfy-Org

    • diffusion_models/minimax_h3_image_pruned_int8_convrot.safetensors (21 GB)

    • text_encoders/qwen3vl_32b_minimax_h3_int8_convrot.safetensors (25 GB)

    • vae/minimax_h3_image_vae_fp16.safetensors (1.2 GB)

    Needs ComfyUI master from 2026-11-12 or newer.

    Known misses

    • Small logo text on clothing garbles. Big signs, menus, banners, labels and headlines hold.

    • Rows of small book spines come out partly gibberish.

    • Tiny background faces in a crowd stay soft, even at 16 MP.

    • A label you call "plain" comes out blank. Write the label text.

    • Text glitches in your pick carry into the final. Pick the seed with the cleanest text.

    Gallery: scenes straight out of this workflow, plus a city set rendered with the same model on a Mac (its post notes say what was retouched). Prompts, aspect ratios, the 4 hunted seeds and the pick for each are in demos.json.

    Legacy v1/v2 (edit + inpaint)

    v1 and v2 used the H3 video model as a single-frame image editor: edit, mask inpaint and a 16 MP route, for Mac and NVIDIA, with custom nodes. They stay downloadable on their version tabs, but their GitHub repo is no longer public and the Mac recipe relied on a turbo LoRA and GGUF files that are now outdated. For new work use v3.0.

    Description

    h3image v0.3.0 — now Mac AND CUDA. 4 ComfyUI workflows (edit + mask-editor inpaint, for Apple Silicon and for CUDA int8_convrot), laid out in numbered groups with a how-to note and a preloaded demo. New Mac recipe: Parasyte turbo LoRA (er_sde / beta57, 8 steps) + video VAE. Repo renamed to github.com/Bambushu/h3image. Verified end to end on an M5 and an RTX PRO 4500 (2026-09-23).

    FAQ

    Workflows
    MiniMax H3

    Details

    Downloads
    301
    Platform
    CivitAI
    Platform Status
    Available
    Created
    9/23/2026
    Updated
    11/22/2026
    Deleted
    -

    Files

    minimaxH3ImageEditInpaint_v20.zip

    Mirrors

    minimaxH3ImageEditInpaint_v20.zip

    Mirrors

    h3image_workflows_v0.3.2.zip

    Mirrors

    CivitAI (1 mirrors)