Navigable world model
ABot-World-0-5B
A third-person navigable world stream on main_video. Served on Windflow as a realtime session you can plug into your product and pay for by the second.
Overview
What ABot-World-0-5B does
ABot-World-0-5B is a 5B keyboard-conditioned world model (Wan2.2-TI2V backbone, LongForcing causal student). On Windflow it runs as a realtime session: connect once, steer it with text prompts, a reference image and movement and look controls while it runs, and receive the live stream back on a named output track.
Every model in the catalog speaks the same typed session protocol, so switching between models changes the controls you send, not how you integrate.
- Architecture
- 5B keyboard-conditioned world model (Wan2.2-TI2V backbone, LongForcing causal student)
- Resolution
- 1344 × 768 delivered (896 × 512 generation + learned super-resolution)
- Chunk
- 12-frame AR blocks; held keys are sampled at each block boundary
- Inputs
- A seed image, a text prompt, and persistent movement/camera key state
- Outputs
- A third-person navigable world stream on main_video
- Delivery
- WebSocket (H.264)
- Session protocol
- sdk.realtime.v2
- Price
- $0.0023 per ready second
$0.0023
Per ready second
Billed only while the session is ready
$8.28
Per ready hour
The same rate, held for an hour
Production
Runtime status
Capacity is brought up on demand
Private beta
Access
Request access or a live demo
Other models