Better human motion LoRA for Minimax H3 (T2V/I2V)

Realistic movement and temporal consistency

Settings

Resolution: 720x1280

Weight: 0.4-0.8

Steps: 20-30

Optimal: 1280 @ 30 steps

Demo Video


Support

If you find this model useful, support further AI research:

๐ŸŸก Buy Me a Coffee: https://buymeacoffee.com/vpakarinen

๐Ÿ”ด Ko-fi: https://ko-fi.com/vpakarinen

Downloads last month
469
Inference Providers NEW

This task can take several minutes

Model tree for vpakarinen/better-human-motion-h3-lora

Adapter
(105)
this model

Space using vpakarinen/better-human-motion-h3-lora 1

Collection including vpakarinen/better-human-motion-h3-lora