A prompt beside the result
Three makers print the prompt with the work: Google Flow on each Flow TV clip, StoryShort on each community card, where it often runs to a paragraph, and Flixly on each item in its gallery. From 3 source pages, read 2026-09-25 to 2026-10-25; no maker pays to be listed.
A visible prompt changes what a showcase is for. Instead of admiring a result, a visitor can see how much direction it took and what the model added unasked.
StoryShort also names the model on every card, which makes each one close to a reproducible example: same prompt, same model, similar result.
For story work, look at whether prompts describe a single shot or a whole scene. The longer ones show whether the tool follows a sequence of actions or only a single image.
| Maker | Item | On the page |
|---|---|---|
| Google Flow | Story | The prompt shown beside each clip, with a button to reuse it |
| StoryShort | Story | The full prompt printed with each video |
| StoryShort | Model | Model named on each video: 10 Sora 2, 5 Veo 3 and 9 Wan 2.5 |
| Flixly | Story | The full prompt kept with each item |
Inclusion rule. Readings from the index cited on this page. Order. The order the page takes them in.
1In the makers' own words
Hide Prompt Reuse Prompt Text to Video
Google Flow, Flow TV player
A highly-trained operative, KIRA (30s, tactical gear, wet hair), sprints through a deluge of rain onto a dimly lit, futuristic rooftop helipad.
StoryShort, community page
SORA 2
StoryShort, community page
Each gallery item includes the full prompt
Flixly, community gallery
- Clip panelThe prompt shown beside each clip, with a button to reuse it
- Video cardThe full prompt printed with each video
- Video cardModel named on each video: 10 Sora 2, 5 Veo 3 and 9 Wan 2.5
- GalleryThe full prompt kept with each item
2From a pipeline that ships episodes
The finished work behind “A prompt beside the result” is made in steps; SceneMixer's guides describe them:
Measured across every job that finished successfully on scenemixer.com in the thirty days to 20 September 2026: analysis of a whole book runs about 2 minutes 49 seconds at the median, one episode's storyboard 1 minute 54 seconds, one video segment 3 minutes 20 seconds, and compositing an episode 3 minutes 52 seconds.
SceneMixer, Turn a Novel into a Video Series with AI — “How long does it take to produce one episode?” (read 2026-10-13)
Under the player of every finished segment sits Edit this clip, with three tabs.
SceneMixer, Edit This Clip: Trim, AI Visuals or Redub, and When to Regenerate Instead (read 2026-10-13)