Sign inGet started
Model ยท Civitai

sandpies/Hand Tie Clips โ€” multi-hop MiniMax H3 video + audio, one queue

Turn 8-second MiniMax H3 clips into 1-minute+ multi-shot films โ€” same face, same voice, synced dialogue, solo shot retakes, and 2 MP guided upscaling โ€” all from one ComfyUI node. ๐Ÿ•น๏ธ Try the Interactive Node UI in Your Browser (click through Script, Refs, Timeline, Swap โš™ RUN before installing) ๐Ÿ“ฆ GitHub Repository ยท Hugging Face Mirror ๐ŸŽฌ What You Can Do Simple Mode (Standard MMH3 ref2va / t2va + Realism Boost): Paste standard 6-field MiniMax H3 ref2va / t2va prompts (passed through verbatim!) or plain prose for single-clip generations ( chains = 1 ) with the visual REFS rail, realism_boost:

Author / organizationsandpies
Downloads954 (as reported by Civitai)
Likes34
Tasktext-to-image
Created18 October 2026
Last updated at sourceโ€”
text-to-imageworkflowsminimax h3tool
Embed this entry
<iframe src="https://silytics.si/embed/item/8b6ce7cb-26f0-4240-9089-217292b5b75a" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

More from sandpies

Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 18 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.