Natural face & speech LoRA for Minimax H3 (T2V/I2V)

Full face muscle dynamics with clear English speech

V2 is out! features multi-gender male/female voice with flawless speech sync and crystal clear quality

Settings

Resolution: 720x1280

Weight: 0.6-0.8

Steps: 20-30

Optimal: 1280 @ 30 steps (9:16)

Prompt: he is speaking into a mic, he maintains eye contact with the viewer saying: 'text here'

Pro Tip: to prevent voice drift, use fixed seed and start your text with the same word (hey guys,)

Demo 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