input
Build a pipeline of AI models
Image, video, audio and text are nodes of one graph. Change one node — only it and what follows is recomputed.
You can build a graph without signing up. Sign-in is needed to run it.
wooden table, daylight from a window, top-down angled view
00:14
running00:42
00:08
waits for video
Popular
Pay for what changed
Drops are charged for every node that runs. Finished results stay in the cache, and a good result can be pinned so it is never recomputed.
| Node | First run | Changed the background description | Changed the voice-over text |
|---|---|---|---|
| Remove background | 2 | cached | cached |
| New background | 8 | 8 | cached |
| Upscale | 3 | pinned | pinned |
| Animate | 18 | 18 | cached |
| Voice-over | 4 | cached | 4 |
| Add sound | 1 | 1 | 1 |
| Total, drops | 36 | 27 | 5 |