AI video generator for MiniMax H3 Max with text, image, and video-to-video workflows
Fix closed eyes in photos using a reference photo
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Freemium
Pricing
Starter: 500 credits/month at $9.9/month, Pro: 1,000 credits/month at $16.9/month, Max: 2,500 credits/month at $39.9/month. Text and image generation use 5 credits per output second at 480P and 8 credits per output second at 768P. Video-to-video uses 11 credits per output second base charge plus ref
Free: One shared free generation across all tools with watermarked preview. Paid: 1 purchased Credit ($1.49 single) for clean full-resolution download. High Fidelity 4× downloads use 2 Credits. Credits purchased one-time with no subscription; do not expire.
Key features
Text-to-video generation with prompt direction
Image-to-video with optional start and end frames
Video-to-video with 2–15 second reference clips
Synchronized audio generation with dialogue, music, and effects
5–15 second video duration options
480p and 768p resolution support
H3 Max Director for live scene direction and recording
H3 Max Camera Controls for planned camera movements
Style LoRAs including Realism, Camera Motion, VHS, and Claymation
Multiple AI video models in one workspace
Upload photo and select person with closed eyes
Optional reference photo of same person for guidance
Review before and after results side by side
Generate repair focused on eye area only
One person per operation
Download result as new PNG file
Works in desktop and mobile browsers
30-day photo storage and history
Google account sign-in for purchases
No subscription required
What makes it different
Focused H3 Max workflow optimized for rapid creative decisions and polished output
Synchronized audio generation integrated into the video output
Live credit cost estimates before generation submission
Live scene direction with H3 Max Director streaming tool
Independent service with model-specific controls and workflow clarity
Uses real reference photos instead of guessing eye appearance