Downloads · 30 days
236
31% of all-time downloads
better-human-motion-h3-lora
vpakarinen/better-human-motion-h3-lora
better-human-motion-h3-lora is a text-to-video model from vpakarinen. Use it when you need video from a text prompt. The card lists the license as apache-2.0.
All-time downloads
757
Public
Repo size
328 MB
Likes
80
Public
Repo makeup
Click a slice to open those files.
.safetensors310 MB · 98%
At a glance
- Task
- Text-to-Video
- License
- apache-2.0
- Access
- Public
- Created
- Sep 2, 2026
- Updated
- Oct 18, 2026
- SHA
- df545ebf
Base models
Model card
From the Hugging Face model README
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
<video controls loop muted playsinline width="360" style="max-width: 100%;"> <source src="https://huggingface.co/vpakarinen/better-human-motion-h3-lora/resolve/main/demo_video_6.mp4" type="video/mp4"> Selaimesi ei tue videon toistoa. </video>Support
If you find this model useful, support further AI research:
🟡 Buy Me a Coffee: https://buymeacoffee.com/vpakarinen
🔴 Ko-fi: https://ko-fi.com/vpakarinen
- Task
- Text-to-Video
- License
- apache-2.0
- Languages
- en
- Wavespeed
- live
- Created
- Sep 2, 2026
- Updated
- Oct 18, 2026