A 5 s scene from a text description: GPT Image makes the still, a video model animates it, the Video Editor frames it. Slow camera and atmosphere (a serum bottle in mist), 16:9. A starter for anyone trying text to video for the first time.
This workflow chains 5 nodes: Gemini Omni Flash 1.1, GPT Image 2.5 Flare, HOW TO USE, Scene Brief, and Video Editor. Duplicate it into your account, swap in your own inputs, and run the whole pipeline in one click.
Built by Andrew Adams. Explore the full workflow library.
Workflow preview
Drag to pan, scroll to zoom. 5 nodes.
More like this
UGC Ad Generator
by Andrew Adams
0455
Comments
0 comments
Loading comments...