Sign In
Civitai turns 4. Pick up a hat.
homemodelsimagesvideos3D Modelshubsarticlescomicscruciblesupdatesshop

MiniMax H3 First-Frame Image-to-Video

Updated: Nov 2, 2026

minimax h3image to videoworkflowcomfyui

Download

1 variant available

Config Other

04_MiniMax_H3________.json

33.64 KB

Verified:

Type
Workflows
Stats

23

Reviews

(2)

Published

Nov 2, 2026

Base Model

MiniMax H3

Hash
AutoV26DFE9A5A03

The MiniMax H3 Community License Agreement’s grant excludes the European Union, the United Kingdom, the Republic of Korea and the United States of America.

MiniMax H3

04.jpg


RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2084850825154875394?inviteCode=rh-v1111

MiniMax H3 First-frame image-to-video

A MiniMax H3 omni-modal video graph exported from episode 288. 25 nodes / 28 links. One LoadImage input used as the starting frame. 9:16 portrait at 0.8 MP, 10 s.

Saved configuration

  • UNETLoader minimax_h3_fl2va_bf16.safetensors; CLIPLoader qwen3vl_32b_minimax_h3_int8_convrot.safetensors (type minimax); VAELoader video minimax_h3_video_vae_fp16.safetensors + audio minimax_h3_audio_vae_fp32.safetensors.
  • The saved graphs contain no LoRA nodes.
  • Sampling: KSamplerSelect res_multistep with BasicScheduler simple, 20 steps, denoise 1; SamplerCustomAdvanced for the custom chain.
  • Conditioning: MiniMaxH3ImageToVideo / MiniMaxH3ReferenceToVideo saved at 1344x768 / 124 / match where present; ResolutionSelector and duration values are quoted per item above; output goes to SaveVideo prefix video/MiniMax_H3.

How to use

The saved prompt preserves a female swordswoman's identity, costume and sword. Single image, no ending-frame anchor.

Limits and not-verified items

No inference was run for this listing: no speed, VRAM, audio-sync or quality claim is made. Values are quoted from the saved nodes. The graph's notes link the official Comfy-Org/MiniMax-H3 model files and the MiniMax blog; those notes are preserved and this listing does not claim to be the original template author. Weights, encoder and VAEs are not bundled; check their licenses separately. The cover image is a promotional still, not a frame produced by this graph.

Tutorial: YouTube · Bilibili. Workflows supplied through AI-KSK; verify workflow, node, model, image/audio and cover rights separately. No blanket commercial or redistribution license is asserted.