Sign In
homemodelsimagesvideos3D Modelshubsarticlescomicscruciblesupdatesshop

H3 Long Video – One Prompt, Any Length (MiniMax H3 ComfyUI Workflow)

Updated: Oct 9, 2026

toolminimax h3ref2vavideolong videoworkflow

Download

1 variant available

Archive Other

H3-Long-Video-Workflows.zip

13.6 KB

Verified:

Type
Workflows
Stats

162

Reviews

(9)

Published

Oct 9, 2026

Base Model

MiniMax H3

Hash
AutoV2
3EBD2A079E
default creator card background decoration
Tool Creators position #97

#97

Followers - 4

4

Likes - 9

9

License:

MiniMax H3 Community License Agreement

Generation, training and LoRA distribution on Civitai are covered by Civitai’s own license agreement with MiniMax. If you download these weights and run them yourself, your use is instead governed by the MiniMax H3 Community License Agreement, whose grant excludes the European Union, the United Kingdom, the Republic of Korea and the United States of America.

MiniMax H3

1-long-video-simple.png

Generate long MiniMax H3 videos from one prompt and one total duration — no manual Save/Load latent steps.

Custom nodes on GitHub: https://github.com/ooizj/ComfyUI-H3-Motion-Context

Based on NikoDemon80/ComfyUI-H3-Motion-Context. The original version chains clips by hand with Motion Context Save/Load latent nodes. This fork removes those steps: H3 Long Video (Simple) works out the segment count, samples each segment, continues from the previous video/audio latent, trims the overlap and joins everything at 24 fps in one run.

What's in the zip

  • H3 Long Video - Simple.json: type the prompt directly and load the first frame and reference pictures with Load Image nodes.

  • H3 Long Video - Ref Prompt Builder.json: manage reference pictures and the six Ref2VA prompt sections in a visual editor, then connect it to Long Video.

Install

cd ComfyUI/custom_nodes
git clone https://github.com/ooizj/ComfyUI-H3-Motion-Context.git comfyui-h3-motion-context

Restart ComfyUI and refresh the browser. Requires a recent ComfyUI with native MiniMax H3 and Concatenate Video support.

Models: https://huggingface.co/Comfy-Org/MiniMax-H3 (diffusion model, Qwen3-VL text encoder, video VAE, audio VAE). After importing, pick your own installed models and images.

Main features

  • One prompt, any length: set total_seconds (e.g. 30) and segment_seconds (e.g. 15); segments are chained automatically with picture and sound continuity.

  • Reference pictures across all segments: <Picture N> references stay consistent for the whole video (Ref2VA), plus an optional first frame.

  • Optional automatic prompt splitting: connect H3 Prompt API (any OpenAI-compatible API, e.g. DeepSeek) and the full-video timeline/dialogue is rewritten per segment, avoiding repeated openings and cut-off lines. Leave it disconnected to skip it entirely — no API calls.

  • H3 Ref Prompt Builder: drag/paste/reorder reference pictures, references renumber automatically, six prompt fields, optional AI tidy-up.

  • H3 Image & Prompt: one text box plus pictures, with local backup/load of prompts and images.

Tips

  • API keys are empty in the shared files; enter your own only if you use the Prompt API.

  • Shorter segments use less memory per pass but add continuation overhead.

  • Questions and bug reports: GitHub Issues.

中文说明

一个提示词 + 总时长，直接生成 MiniMax H3 长视频。基于 NikoDemon80/ComfyUI-H3-Motion-Context，去掉了手动的 context Save/Load 步骤：H3 Long Video (Simple) 节点会自动计算分段数、逐段采样、承接上一段的视频和音频 latent、裁掉重叠部分，最后以 24 fps 拼接输出，一次运行就完成。

  • 压缩包里有两个工作流：Simple（直接写提示词，用加载图像节点接首帧和参考图）和 Ref Prompt Builder（可视化管理参考图和六段提示词）。

  • 安装：在 ComfyUI/custom_nodes 下 git clone https://github.com/ooizj/ComfyUI-H3-Motion-Context.git comfyui-h3-motion-context，重启 ComfyUI 并刷新浏览器。

  • 可选接入 H3 Prompt API（OpenAI 兼容接口，比如 DeepSeek），自动按段改写提示词；不接则不会调用任何 API。

  • 导入后请换成你自己安装的模型和图片；API key 已清空。

GPL-3.0 · 欢迎 Star 和反馈 Issue！