Features
Image generation — text-to-image, image-to-image, edit
Video generation — text-to-video, image-to-video, video-edit, extend
Avatar generation — digital human, lipsync
Audio generation — text-to-music, voice cloning, TTS
LLM API — Claude Opus 4.8, GPT-5.5, Gemini 3.1 Pro, DeepSeek V4 Pro
LoRA training and inference
Webhook support for async workflows
Streaming support for real-time outputs
Base64 output and synchronous mode
Desktop app with full inference engine
CLI tool for command-line access
Python and JavaScript SDKs
Seedance 2.0 models with 15% discount
Nano Banana 2 image model ($0.07/image)
Serverless GPU deployment for custom models
Agent One autonomous AI agent for video creation
Long-term memory for consistent clips across projects
Edit multiple shots simultaneously (costumes, locations, characters)
AI-assisted scriptwriting and storyboarding
Full timeline editor with AI capabilities
Real-time multiplayer collaboration with live cursors
Access to 200+ AI models (video, image, audio, music)
AI voice generator and voice cloning
AI video translator and subtitles
Custom agent creation (cinematographer, sound designer, etc.)
Stock media integration (iStock, Storyblocks)
Face swap and other quick AI tools
AI image generation and enhancement
SOC 2 & ISO aligned, GDPR compliant
