CivArchive
    Flow Image — stills from a video model — ComfyUI workflow (Gmanski) - v1.0
    NSFW
    Preview 144898212

    📌 Overview

    A photoreal still out of MiniMax H3.

    H3 has no image mode; this renders the shortest valid clip and keeps its settled middle frame, with a photoreal LoRA. Includes the Advanced variant.

    ✅ What you get

    • Flow (Image) and Flow (Image Advanced)

    🧰 What you need

    • 48 GB VRAM

    • VRAM: 48 GB+ · Level: Beginner

    📦 Models and packs

    Uses the minimax-h3-image pack from the Gmanski RunPod template, which installs every checkpoint, LoRA and custom node this workflow needs in one click.

    ⬇️ Download

    Free. The workflow JSON is attached to this listing. Full notes, tested settings and the exact model packs are on its page:

    👉 Workflow page on gmanski.com

    💬 Help

    Questions? Our Discord bot answers most things in under a minute, and a human follows up.

    ⚠️ Disclaimer

    Every face in the samples is a generated character, not a real person. Use responsibly and within the law where you live.


    Gmanski makes ComfyUI workflows, a one-click RunPod template, custom nodes and ready-made AI characters: gmanski.com


    Description

    Comments (1)

    yajukunOct 7, 2026
    CivitAI

    Hi, in order to run this WF we need 48GB of VRAM? Is this more of a runpod type WF?

    Workflows
    Other

    Details

    Downloads
    21
    Platform
    CivitAI
    Platform Status
    Available
    Created
    10/7/2026
    Updated
    10/8/2026
    Deleted
    -

    Files

    flowImageStillsFromAVideo_v10.json

    Mirrors