Model · Civitai
AdaptiveVision/Natural Face & Speech Minimax H3
Face and speech dynamics for Minimax H3 Full face muscle dynamics with clear English speech Trained on T2V but supports also I2V 720x1280 resolution with 15-30 steps Weight 0.6-0.8 is recommended Pro Tip: to prevent voice drift, use fixed seed and start your text with the same word (hey guys,) Prompt: she is speaking into a mic, she maintains eye contact with the viewer saying: 'text here'
| Author / organization | AdaptiveVision |
|---|---|
| Downloads | 3.9K (as reported by Civitai) |
| Likes | 168 |
| Task | text-to-image |
| Created | 19 September 2026 |
| Last updated at source | — |
Popularity, last 3 days
3,906 now (+76 since 2026-10-15). Counts as reported by the source, snapshotted daily by Silytics.
More from AdaptiveVision
Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.