update 1.1 added text2image gen on same WF with swtich++Help keep a character on-model” is accurate; it improves consistency without training a LoRA, but doesn’t guarantee an exact face match.++This workflow turns a folder of reference images of one character into a reusable H3 RefMod. Load that file into your MiniMax H3 Continuum video workflow to help keep the character’s face and appearance consistent across scenes. It supports realistic or anime references; it doesn’t generate the movie itself.For MY use, the face is the main goal, yes—but a RefMod can also carry hair, body shape, clothing, and visual style from its reference pictures. It isn’t a face-only lock. but I have not used itRight now, I’ve only used it for faces. It’s a simpler way to help keep a character on-model in short videos without training a LoRA.t’s a saved reference-conditioning file, not a trained checkpoint or LoRA. The baker encodes your reference images for H3 to use without retraining the underlying model.

RefMod baker

How to use this workflow1. Make your pictures<ol><li>On the group switch, turn on Text2Image. The baking group turns off automatically.</li><li>Write your image prompt and choose your settings.</li><li>Press Run.</li><li>Your pictures save here: <code>D:\AI\ComfyUI\ComfyUI\output\Krea2\</code></li><li>Repeat until you have the character pictures you want.</li></ol>2. Choose pictures for the RefMod<ol><li>Open that output folder in File Explorer.</li><li>Create a folder named after your character.</li><li>Copy only your good pictures into it. Include different angles, with a clear, consistent face.</li><li>Keep rejected pictures and other characters out. The baker reads every picture in the selected folder, up to 32.</li></ol>3. Bake the RefMod<ol><li>On the group switch, turn on Bake RefMods here. Text2Image turns off automatically.</li><li>In the folder loader, enter your character’s picture-folder path.</li><li>In the baker, choose a new, unique name for the RefMod. It currently says <code>notSidney</code>; reusing an existing name risks replacing that file.</li><li>Leave the H3 baking VAE as: <code>minimaxh3\minimax_h3_video_vae_int8_convrot.safetensors</code></li><li>Press Run.</li><li>Your baked file saves here: <code>D:\AI\models\refmods\</code></li></ol>4. Use it in Continuum<ol><li>Open your H3 Continuum workflow.</li><li>Select the new file in Load H3 RefMods.</li><li>Keep the RefMod Bridge connected to the Continuum Sampler’s model input.</li></ol>The RefMod is for MiniMax H3 video—not Krea image generation. To make more pictures, switch back to Text2Image. Press Ctrl+S whenever you want to save your workflow changes.

Files with SHA256: 23421acbad3f1e99ca1d0ce9aeb435c67816d8b4d76d9adb1dba61967a6b4786