Your photo keeps its size and place; only the new space around it is painted, so faces and details are untouched.
3
Steer what appears
Leave it to the model, or say what belongs in the new space: more sky, the rest of the room, a crowd behind you.
Models
The model behind it
GPT Image 2.5OpenAI · 1K resolution
1 credit an image
Square, portrait, story or wide
Up to 3 reference photos
How to use the AI Image Extender
Upload a photo
Any photo you want bigger or in another shape.
Pick the new format
Wide, story, square or portrait. Add a note about the new space if you like.
Generate
The extended image is ready in about 20 to 40 seconds.
What is the videosi AI Image Extender?
The AI Image Extender, also called uncrop or outpainting, grows a photo past its edges with GPT Image 2.5. You choose the new format and the model paints the missing scene so it matches the original.
It is the quick fix for a photo in the wrong shape: a YouTube thumbnail from a phone shot, a story from a landscape, or room for text on a banner.
One image costs 1 credit, shown before you start. A new account's first image is free and carries a videosi watermark; removing the watermark costs 1 credit. A render that fails returns its credits automatically.
Which model does the videosi AI Image Extender use?
GPT Image 2.5 by OpenAI, at 1K resolution. It follows long prompts closely, writes legible text inside images and keeps faces from a reference photo recognisable.
Can I use the images commercially?
Yes, images you make with credits are yours to use, including commercially, as long as the prompt and any photos you upload are yours to use and follow our acceptable use policy.
Can I turn the image into a video?
Yes. Under every finished image there is an Animate button: it opens Image to Video with the image already loaded, and you describe the motion.
