CivArchive
    H3MD Director 0.5 – 2–3 min videos with MiniMax H3: multi-character swap, wide-shot face refine, seamless CCW - v0.5.8 keyframe mask fix
    NSFW

    New in 0.5 (v0.5.5): multi-character swap – swap 3–5 people in one video without H3 mixing them up when they cross or overlap. The Qwen Image 2.1 Keyframe workflow redraws the key moments with your character pictures (about 2–3 min for a 26 s clip) and saves a plan you import on the Director. Plus face refine for wide shots: small faces are redrawn inside a head mask and come out much clearer. Tutorial (EP08): https://youtu.be/WMQJjmHZikc – details in "About this version" on the right.

    Most video workflows stop at 10–15 seconds. H3MD Director is a free, open-source ComfyUI node pack that renders 2–3 minute videos with MiniMax H3 in one run – one continuous take, or a sequence of planned shots.

    中文简介在下方 ↓

    At a glance

    • Two modes: 0.3.x renders segment by segment – each segment continues from the last 1.6 s of the one before. 0.4 adds Seamless long video (CCW, Chained Context Windows) – the whole take is rendered on one timeline. One tick box on the Director switches between them.

    • Measured on one RTX 5090: a 2 min 20 s 1080p music video with Seamless long video in 2 h 18 min (10 shots, 3 groups, 48 fps), compute VRAM peak 11.1 GB. Full numbers in "About this version" on the right.

    • VRAM: 16 GB minimum, 24 GB+ recommended; the 4B text encoder option saves 10+ GB.

    • What you can make: music videos with lip-sync, motion copy, text-to-video. On the Director panel you plan every shot – length, prompt, reference pictures, locked audio.

    • Examples: the gallery above; open the showcase post to see each clip's settings.

    What's new in 0.4

    • CCW – Chained Context Windows: tick "Seamless long video" on the Director. Continued shots render together on one timeline – no continuation seams, no drift, no double images where windows overlap. Hard cuts stay clean. Needs ComfyUI 0.44+.

    • Redraw a few seconds: the H3MD Redraw / Preview node re-renders only the seconds you type (e.g. 1:12-1:15); you can change that shot's prompt or pictures first. Everything else stays frame-identical.

    • 8-bit cache in the example workflows: about 9 GB per minute of 1080p instead of 18 GB, no visible difference.

    • Frame interpolation (48 / 60 fps) no longer blends two shots at a hard cut. 0.4.3: lighter Control Panel – each LoRA dropdown loads the full list only when you open it.

    Earlier, in 0.3: the simple workflow (one Control Panel + the Director), the "Which segments" box to redo only some segments, plan export / import as one zip, and optional drift correction on save.

    Install

    1. ComfyUI 0.43+ (native MiniMax H3); 0.44+ for Seamless long video.

    2. ComfyUI Manager → search "H3MD Director", or clone the GitHub repo into custom_nodes.

    3. Drag H3MD Director simple.json from the zip onto the canvas.

    GitHub (docs, model table, prompt guide): https://github.com/1113800942/comfy-h3md-director

    Tutorials on YouTube: https://www.youtube.com/channel/UC1H4UDuSqD6M7BqLUlVy9lA

    Install + first long video (EP02): https://youtu.be/zvPqr6ihZic

    Seamless long video + redraw a few seconds (EP03): https://youtu.be/k0jZIbaH-aA

    Previous version page (v0.1.1): https://civarchive.com/models/3032684

    Full technical details (measured speed and memory, model files and where they go, optional parts): open "About this version" on the right, or see the GitHub README.

    Run it online (no GPU needed)

    RunningHub – cloud ComfyUI with ready-made workflows.

    Three ready-to-run H3MD apps on RunningHub (referral links: the invite code gets you a discount, and it also supports this project):

    • AI short drama, 6 shots, swap the images and the story: https://www.runninghub.ai/ai-detail/2120401708354838530?inviteCode=aolwbd1n

    • Long music video, one photo + one song: https://www.runninghub.ai/ai-detail/2120407904939876354?inviteCode=aolwbd1n

    • Motion copy, your photo follows any video: https://www.runninghub.ai/ai-detail/2120413562564083713?inviteCode=aolwbd1n

    H3MD Director workflow on RunningHub: https://www.runninghub.ai/zh-cn/post/2117897074309345281

    中文简介

    0.5 新功能(v0.5.5):多角色替换,一个视频里换 3–5 个人,人物换位、前后重叠时也不换错;用 Qwen Image 2.1 关键帧工作流在关键时刻先把人换好(26 秒原片约 2–3 分钟),打包成计划包导入导演台即可。另有远景修脸:远景小脸在头部遮罩内重画,清楚很多。教程(EP08):https://youtu.be/WMQJjmHZikc

    H3MD Director 是免费开源的 ComfyUI 节点包,用 MiniMax H3 一次生成 2–3 分钟的长视频:可以是一整个长镜头,也可以是按计划排好的一组镜头。

    • 两种生成方式:0.3.x 是分段式,一段接一段生成,每段从上一段最后 1.6 秒接着往下走;0.4 增加了无接缝的窗口式(接续窗口 CCW),整条长镜头放在一条时间线上一起生成。导演台上勾一下就能切换。

    • 0.4 无接缝长视频(接续窗口 CCW):在导演台顶部勾「Seamless long video」,接续的镜头放在同一条时间线上一起生成,段与段之间没有接缝、不漂移,窗口重叠的地方也不重影;硬切照样干净。需要 ComfyUI 0.44 以上。

    • 局部重绘:「H3MD Redraw / Preview」节点只重跑你填的那几秒(如 1:12-1:15),可以先改这个镜头的提示词或参考图,其余画面逐帧不变。

    • 缓存改 8 位:1080p 每分钟约 9 GB(原来约 18 GB),画质看不出差别。

    • 实测 RTX 5090:2 分 20 秒的 MV(1920×1088,10 个镜头,3 组,48 fps)2 小时 18 分钟,计算显存峰值 11.1 GB;比分段式慢约 25%。

    • 安装:ComfyUI Manager 搜「H3MD Director」,或把 GitHub 仓库克隆到 custom_nodes,再把压缩包里的工作流拖进画布。国内镜像:huggingface.co/yj0942/H3MD-Director(打不开可以把 huggingface.co 换成 hf-mirror.com)。

    • 教程视频是中文讲解(带中英字幕),第三集:https://youtu.be/k0jZIbaH-aA

    • 没有显卡也能跑:RunningHub 上三个现成应用(邀请链接,用邀请码有优惠):

     – AI 短剧(6 镜头可换图换剧情):https://www.runninghub.ai/ai-detail/2120401708354838530?inviteCode=aolwbd1n

     – MV(一张照片 + 一首歌):https://www.runninghub.ai/ai-detail/2120407904939876354?inviteCode=aolwbd1n

     – 动作复刻(照片跟着视频动):https://www.runninghub.ai/ai-detail/2120413562564083713?inviteCode=aolwbd1n

    License

    • H3MD nodes: AGPL-3.0. MiniMax H3 weights are not included and have their own license.

    • The RunningHub links are invite links (new sign-ups get a discount).

    Sample videos are our own, made with H3MD: v0.4.3 – Peter, from the 0.4 seamless music-video test; v0.3.3 – Eve, "Above the Clouds" (song made with ACE-Step 1.5).

    Built on ideas and work from Luna, Niko, Marker, LBH-123-AI, Kijai, T8 and others – thank you. License: AGPL-3.0 with attribution.

    Description

    0.5.8: cleaner multi-character swap keyframes (small improvement to the keyframe mask step). New node H3MD Keyframe 1b: Recast redraws people one after another, each crop cut from the frame where the people before her are already recast, so bits of a bigger original (wig, ears, tail, wide skirt, apron, socks) are no longer left around the new person. Slider mask_grow (default 0.25; 0.3-0.35 for cosplay-sized originals). Prepare now finds the source's cuts and puts at least one keyframe in every shot, so nobody is drawn twice after a cut. Tip: write shoes, legwear and what she does not wear in each description line ("bare legs, black heels; no socks, no boots"). The Keyframe workflow in this zip uses Recast; the Director workflows are unchanged. Update the nodes via ComfyUI Manager or git pull.

    FAQ

    Workflows
    MiniMax H3

    Details

    Downloads
    137
    Platform
    CivitAI
    Platform Status
    Available
    Created
    11/20/2026
    Updated
    11/20/2026
    Deleted
    -

    Files

    H3MD_Director_v0.5.8_workflows.zip

    Mirrors