AI Storyboard & Scene Image Generator
Under maintenancePricing
from $50.00 / 1,000 scene image generateds
AI Storyboard & Scene Image Generator
Under maintenanceTurn a story or script into a sequence of consistent AI images — one per scene. Give it a story (it splits into scenes) or your own scene list, a shared art style, and optional character notes. For faceless videos, comics, ads, pitches, and animatics.
Pricing
from $50.00 / 1,000 scene image generateds
Rating
0.0
(0)
Developer
Dami's Studio
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
2 days ago
Last modified
Categories
Share
Turn a story or script into a sequence of AI scene images, one per scene, that share a consistent art style and character look. Hand it a block of text and it works out the scenes for you, or pass your own scene list if you'd rather control the breakdown. Built for faceless videos, comics, ad concepts, and pitch decks where you need a run of related shots instead of a single one-off picture.
How it works
If you give it a story, a chat model (gpt-4o-mini) splits it into N short visual scene descriptions, keeping the same characters and setting across them. Each scene is then rendered with gpt-image-1, with your style and characters notes prepended to every prompt so the look stays consistent shot to shot.
Input
You can run with just a story (everything else has sensible defaults) or skip splitting entirely by passing your own scenes. Nothing is strictly required, but you do need an OpenAI key, either as openaiApiKey or the OPENAI_API_KEY environment variable.
| Field | Required | Notes |
|---|---|---|
story | no | A story or script. Gets split into scenes automatically. Leave empty if you supply scenes. |
scenes | no | Your own array of scene descriptions, one image each. Overrides automatic splitting. |
numScenes | no | How many scenes to split a story into. Default 6, range 1-20. Ignored when you pass scenes. |
style | no | Shared art style applied to every image. Default is a cinematic look. |
characters | no | Recurring character notes for continuity, e.g. "an old bearded keeper in a yellow raincoat". |
aspectRatio | no | 9:16, 16:9, or 1:1. Default 9:16. |
quality | no | gpt-image-1 quality: low, medium, or high. Default high. |
openaiApiKey | no* | Your OpenAI key, used for both splitting and image generation. Required unless OPENAI_API_KEY is set. |
baseUrl | no | OpenAI-compatible base URL if you're routing through a proxy. Defaults to the OpenAI API. |
Output
The dataset gets one record per scene. Each record has index, the scene text, the full prompt that was sent, and imageKey / imageUrl pointing at the PNG in the run's key-value store, plus aspectRatio and size. Records that fail come back with ok: false and an error field, so a single bad scene won't kill the run.
Example
Pricing
$0.05 per image, pay per result, no subscription. You bring your own OpenAI key, so the gpt-4o-mini and gpt-image-1 calls are billed to your own OpenAI account on top.
Notes
Continuity is prompt-based, not a locked reference image, so characters stay close but won't be pixel-identical across every scene. Tighter characters notes and a specific style help a lot. Higher quality costs more on your OpenAI bill and runs slower.
