Is my photo uploaded?

No — this page has no input image. Text-to-image sends only the sentence you typed. The one to distinguish it from is «AI scene editing», which takes a photo of yours and modifies it, so that page does upload — and says so at its entry point and in its text. As for compressing, cropping, cutting out and the rest: all of that finishes in your browser with nothing leaving.

Guests get a free daily allowance; beyond it you'll need an account (registering is free). How many are left is on the «Is AI editing free» page, where the numbers are read live from the API. Every generation spends one, including the one you run because you didn't like the last — a cloud call costs us real money and we won't hide that.

Can I use the output commercially?

That depends on the terms of the model provider behind it, not on us, so we're not going to hand you a «yes, go ahead commercially» here — that's a promise we have no standing to make. The sensible approach: treat it as material rather than a finished piece, and check the current terms yourself before anything that matters. What we can promise is the other half: we don't reuse your results.

It doesn't look like what I described. Now what?

Usually the prompt is too short. The model can't see the picture in your head, so separating subject, style, light and framing beats piling on adjectives: «a cat» → «a ginger cat on a wooden windowsill in warm light, shallow depth of field, film grain». Also don't expect accurate lettering or hands — those are the well-known weak spots of this kind of model. If you need text, add it afterwards with the editor's text tool, where it also stays editable.

AI image generation: write a sentence, get a picture, keep editing it

Generating isn't the finish line. The moment the image lands on the canvas, you still have a whole editor.

Use it online now

Most text-to-image tools end at «download»: generate, glance, rewrite the prompt, try again. But what usually happens next is editing — crop off the excess, warm it up a little, add a line of text, combine it with another picture. Here generation sits inside the editor: the result is a layer, and from there you use the same tools as always, with no export-and-reimport in between.

This page doesn't upload your images, because it doesn't need any. The input to text-to-image is the prompt, and that is all that gets sent. (By contrast, «AI scene editing» takes a photo of yours and changes it — that page does upload, and says so.) The generation itself runs in the cloud, roughly half a minute to two minutes per go; guests have a free daily allowance and need an account beyond it.

Key features

The result is a layer, not a file you can only download

Press «apply» and the image becomes a new layer in the current document. From there: crop, curves, text, masks, compositing with other layers — whatever the editor has, this image can use.

Optional transparent background

Tick «transparent» and a cut-out pass runs right after generation, giving you an element you can drop onto something else. That cut-out runs in your browser; nothing extra is uploaded.

You can generate into a selection

Draw a box on the canvas first and the result lands inside it — far less work than redrawing the whole frame when you only want to replace a region or fill a corner. No selection means the whole canvas.

Cancel while you wait

A progress bar runs; change your mind and press cancel. A go usually takes half a minute to two minutes, longer for elaborate prompts (ceiling about five minutes).

How to use

1
Open a document first

The generated image has to land somewhere, so create one at the size you want (or open an existing picture).
2
Write the sentence

The more specific the better: subject, style, light, framing. «A cat» and «a ginger cat on a wooden windowsill in warm light, shallow depth of field» are worlds apart.
3
Wait

Usually half a minute to two minutes. The canvas stays usable meanwhile, and you can cancel at any point.
4
Apply, then keep editing

«Apply» turns it into a layer; crop and adjust from there. Don't like it — delete the layer and go again, keeping in mind that each generation spends an allowance.

FAQ

Is my photo uploaded?: No — this page has no input image. Text-to-image sends only the sentence you typed. The one to distinguish it from is «AI scene editing», which takes a photo of yours and modifies it, so that page does upload — and says so at its entry point and in its text. As for compressing, cropping, cutting out and the rest: all of that finishes in your browser with nothing leaving.
Is it free?: Guests get a free daily allowance; beyond it you'll need an account (registering is free). How many are left is on the «Is AI editing free» page, where the numbers are read live from the API. Every generation spends one, including the one you run because you didn't like the last — a cloud call costs us real money and we won't hide that.
Can I use the output commercially?: That depends on the terms of the model provider behind it, not on us, so we're not going to hand you a «yes, go ahead commercially» here — that's a promise we have no standing to make. The sensible approach: treat it as material rather than a finished piece, and check the current terms yourself before anything that matters. What we can promise is the other half: we don't reuse your results.
It doesn't look like what I described. Now what?: Usually the prompt is too short. The model can't see the picture in your head, so separating subject, style, light and framing beats piling on adjectives: «a cat» → «a ginger cat on a wooden windowsill in warm light, shallow depth of field, film grain». Also don't expect accurate lettering or hands — those are the well-known weak spots of this kind of model. If you need text, add it afterwards with the editor's text tool, where it also stays editable.

Try AI image generation: write a sentence, get a picture, keep editing it now

Runs fully in your browser · no install · no signup · images never uploaded

Use it online now