Free trial available. After trial: $0.039 per image generation.
Starter: USD $5.99 one time for 10 credits (one standard 12-second video). Creator: USD $9.99 one time for 20 credits (one APT video or two standard 12-second videos). Video costs: 5 seconds = 5 credits, 8 seconds = 7 credits, 12 seconds = 10 credits, 15 seconds = 13 credits. APT duet (15 seconds, 7
Key features
4K image generation with native 2K rendering and seamless 4K upscaling
Perfect text rendering with 95%+ accuracy in 100+ languages
Multi-image fusion: blend up to 3 images with automatic style harmonization
Fast generation: under 10 seconds per image
Text prompt, image-to-image, and sketch-based generation modes
Powered by Google Gemini 3.0 Pro infrastructure
Consistent character rendering across multiple images
Commercial-ready outputs with no watermark on free samples
Multiple video lengths (5, 8, 12, 15 seconds)
Resolution options (480P or 720P)
Multiple aspect ratios (9:16, 1:1, 16:9)
Accepts JPG, PNG, or WebP photo files
AI-generated original audio for rap duets
Animated photo effects with 16 choices
Downloadable finished videos
What makes it different
95%+ text accuracy in 100+ languages, industry-leading for text-in-image generation
15% faster than alternatives with native 2K and 4K upscaling
$0.039 per image, 10x cheaper than DALL·E 3
Trusted by 10 million creators worldwide
Multi-image fusion with automatic style harmonization and character consistency
Original AI-generated audio instead of licensed music
One-time credit purchases with no expiration
Flexible video formats with multiple resolutions and aspect ratios
Support for two performers or duet mode from single photo
Immersive stage environments for personalized videos