Pictures from a sentence
Describe a picture. Keep every run.
Pick a shape and how many, press Generate, and the pictures appear one by one in a history that keeps every run with its settings. Make variations, start from a picture of your own, collect favourites and save to Geenius OS Media with the picture's provenance.
Request access What makes the pictures
Early access, and plain about it: today the pictures are made by a Preview that is simulated in your browser, not by an image model. The windows on this site show sample data.
Made bya simulated Preview todayreal models where a key is set
Before anything else
What is simulated.
We would rather say it here than let you find out in the app.
- Pre-betaThe Preview is the maker today
It paints a simple picture in your browser from your words and a seed: a palette that leans with the words, a motif and your sentence set in type. It is real, quick and repeatable, and it does not draw what you described.
- Pre-betaReal models are connected in code
A Gemini image model is wired and works only where its key is set on the server. Whether it is switched on for the hosted app is to be confirmed. Imagen has been retired by Google.
- Not offeredA photographic result
Nothing here promises one.
What it does
Describe. Generate. Keep.
The composer, the history and the library are built and in the app. They work the same with any provider, and each picture says which one made it.
Describe
A sentence, one of eight shapes, one to four pictures, an optional seed.
Make picturesHistory
Every run kept with its settings. Reuse them.
HistoryVary
Variations near a look, or a new picture from a picture of your own.
VariationsKeep
Collections, favourites, downloads, and Geenius OS Media with provenance.
Collections
The composer
A sentence, a shape, a count.
Describe the picture, choose a shape (square, classic, portrait, photo, poster, wide, tall or cinema), one to four pictures and, if you like, a seed and a negative prompt. The composer shows which model will make it. Pictures appear one by one in the history.
- Eight shapes, up to four pictures a run
- The same words and seed give the same Preview picture
- A negative prompt where the model takes one
The history
Every run, with what made it.
Every run stays in the history with its prompt, shape, seed, model and settings, and the state of each picture. Reuse a run's settings, retry a failed one, or delete a run and its pictures for good.
- Runs: queued, running, done or failed
- A picture knows its seed and model
- A failed picture is not counted
Variations
Near a look, or from a picture.
Make variations of a picture you like: same settings, new seeds. Or start a new picture from one: yours, an upload or one from your Geenius OS Media library, with a strength. With the Preview, the picture is painted over rather than edited by a model.
- One to four variations
- Upload or bring a picture from Media
- Strength from 0 to 1
Geenius OS Media
Saved with their provenance.
Save a picture to your Geenius OS Media library together with its words, model, seed and settings, so you can see later what made it. And bring a picture in from Media to start from.
- Provenance travels with the picture
- Collections and favourites in the app
- Downloads any time
A door for your AI
Your AI queues. A page makes.
Connect Claude, ChatGPT or Grok to Geenius OS once. Your AI can ask which providers are ready, queue a run, read the pictures and keep collections. Because the Preview runs in a browser, a queued run is made as soon as somebody in the workspace has AI Pics open.
- Two tools: picture and collection
- On every plan, making pictures on Premium and Max
- It cannot promise a result
In numbers
Facts you can check, not testimonials.
AI Pics is in early access and has no public customers yet. These are things you can look up in the app and the docs today.
- 8shapes, from square to cinema
- 4pictures at most in one run
- 1provider ready for everyone: the simulated Preview
- 0pictures a month on Pro, which is the library
Honest labels
What works today.
We say what is live in early access, what depends on your setup, and what is not offered.
- Pre-betaComposer, history, variations, collections and Media
Built and in the app now. Early access: people request access.
- Pre-betaYour AI through Geenius OS
Works when AI Pics is added to your Geenius OS workspace, on every plan.
- Pre-betaReal image models
Connected in code and ready only where their keys are set. We do not claim they are on for you.
- Not offeredMaking pictures on Pro
Pro is the library. Premium and Max make pictures.
- Not offeredA phone app
Web only for now.
Who it is for
For people who want a library and a maker.
Placeholders and mock-ups
Simulated pictures for layouts and drafts, never passed off as real.
See the setupPicture libraries
Collections, favourites, search and downloads for pictures and their settings.
See the setupGeenius OS users
Start from a picture in Geenius OS Media; save results back with their provenance.
See the setupMakers with their own AI
Your AI asks what is ready, queues a run and keeps collections.
See the setup
Pricing
Three plans. No free tier.
Per month, in euros, VAT included. Included in the matching Geenius OS plan. Payments are in test mode during early access.
- €9Pro: the library, no making
- €19Premium: up to 2,000 pictures a month
- €49Max: up to 5,000 pictures a month
From the blog
Notes on pictures, honestly.
Say what a preview is
Why AI Pics names its Preview as simulated, what the Preview actually does, and why that is the honest starting point for pictures from a sentence.
Seeds make a picture repeatable
What a seed is in AI Pics, how it makes a result repeatable, how variations change it, and why keeping the seed in the history matters.
A history beats a gallery
Why AI Pics keeps every run with its settings instead of only the best pictures, and how that helps you repeat, vary and explain a result.
Questions
Good questions.
What is AI Pics?
A library and a maker for pictures. You describe a picture, choose a shape and how many, and the pictures appear in a history that keeps every run with its settings. You can make variations, start from a picture, keep collections and favourites and save to Geenius OS Media. Its full name is Geenius AI Pics.
Are the pictures made by an AI model?
Not by default today. The Preview that makes them is simulated in your browser: it paints a simple picture from your words and a seed and is not an image model. A real model is connected in code and works only where its key is set on the server.
Will it draw what I describe?
The Preview will not: it paints a palette and a motif that lean with your words and sets your sentence in type. A real model can, where one is switched on.
Is it ready to use?
It is in early access: people request access and payments are in test mode. The composer, history, collections and Media are built. Request access.
Who makes it?
AVS Media, a small company in Nijmegen, the Netherlands, as one of the apps of Geenius OS.
How does my AI use it?
Through Geenius OS: tools called picture and collection. It can check providers, queue a run, read pictures and keep collections.
Describe the first one.
AI Pics lets people in step by step. Ask for a place, or sign in with Geenius OS.