Practical Test of MiniMax H3 TTM Workflow in ComfyUI
Start here
The author kongo_jun built and tested the TTM motion tweening workflow for MiniMax H3 in ComfyUI. Generation took 250 seconds, with GPU memory usage of 71GB. This workflow requires CUDA 13, and involves downloading multiple model files to specified directories, and uses SAM3.1 to designate the moving object and path. The author reports that there are two controllers, which are difficult to adjust.
Written by AI from the reports · updated 3 days ago
Report timeline
Follow the reports to see the event from other sides.
- note · kongo_jun · 图像视频创作分享Trying MiniMax H3's TTM motion tweening tool in ComfyUI
The author built and tested a MiniMax H3 TTM motion tweening workflow in ComfyUI; generation took 250 seconds and GPU memory usage was 71GB. The workflow requires CUDA 13 and downloading multiple model files to specified directories, using SAM3.1 to specify moving objects and paths. The author reports that there are two controllers, which are difficult to adjust.
Heat trend for this event
- Current
- 3
- Peak
- 10Nov 17 01:00
- 24h change
- -50%
The trend compares only sources observed the whole time, so the range may be smaller than the current heat figure. Hover or tap the chart for each hour. Left and right arrow keys move through it.