Every major model.One picker.
Pick one yourself, or let Director choose the right one for each shot. New models show up the week they launch.
MiniMax H3
MiniMax
Near the top for quality at the lowest price
Silent
All plansMiniMax H3 Max
MiniMax
Characters and motion held from references
Silent
All plansWan 3.0
Alibaba
The best with sound: dialogue, music and effects in one take
Yes
Creator+FLUX 3 Max
Black Forest Labs
Long takes up to 20 seconds, cinema-wide frames
Yes
Creator+Kling 4.0
Kuaishou
Kling's newest: big action and camera moves
Silent
Creator+Grok Imagine 1.5
xAI
Stylised clips, always with sound
Silent
All plansKling O3 Pro
Kuaishou
Holding a character across shots from references
Silent
Creator+Veo 3.1
Google
Dialogue with synced sound, realistic people
Yes
Pro+Veo 3.1 Fast
Google
Quick drafts with sound
Yes
Creator+Seedance 2.0
ByteDance
Multi-shot sequences from one prompt
Yes
Creator+Seedance 2.5
ByteDance
Seedance's newest: finer detail and steadier motion, with sound
Yes
Pro+
Thinking models
Director plans films, writes scripts and storyboards, and draws Motion with the model you choose.
Anthropic
- Claude Opus 5.5
- Claude Fable 5.1
- Claude Sonnet 5.5
- Claude Haiku 5.5
- Claude Fable 5
- Claude Opus 4.8
- Claude Sonnet 5
- Claude Haiku 4.5
OpenAI
- GPT-6 Astra
- GPT-6.1 Sol
- GPT-6 Luna
- GPT-5.6 Sol
- GPT-5.6 Terra
- GPT-5.6 Luna
- GPT-5.5
- GPT-5.4
- GPT-5.4 mini
Choosing a model
For people talking on camera with sound, Veo 3.1. For keeping a character the same across shots, Kling O3 Pro with reference images. For quick, cheap drafts, Grok Imagine or Wan. If you're not sure, let Director pick per shot.

Your first film is one sentence away.
Free to start. Pay only for what you render.
