Text-to-Image and Image-to-Image
Create a new image from a prompt or edit a reference image with a natural-language instruction.
Create polished AI images from text or reference images with up to 16 inputs, flexible aspect ratios, and 1K, 2K, or 4K output.

GPT Image 2.5 is available through KIE's Flare workflow for text-to-image generation and image-to-image editing. Choose a supported aspect ratio, send up to 16 reference images, and select 1K, 2K, or 4K resolution for each creation.

A focused workflow for precise text-to-image and image-to-image creation
Create a new image from a prompt or edit a reference image with a natural-language instruction.
Choose the resolution that fits your draft, social post, product visual, or high-detail creative.
Combine up to 16 JPEG, PNG, WEBP, or JPG references for products, characters, style, or composition.
Use auto, square, portrait, landscape, and wider supported ratios for different publishing needs.
The generator clearly applies 6 credits for 1K, 10 credits for 2K, and 16 credits for 4K output.
Kevin Stratvert
Brendan Jowett
Paul J Lipsky
Theoretically Media
The AI Advantage
Joseph Martin
GPT Image 2.5 — Image concepts FAQ
GPT Image 2.5 is an image generation and editing workflow available through KIE Flare. It supports both text-to-image and image-to-image creation.
Yes. Add one or more reference images and describe the changes you want. The generator routes the request through KIE's image-to-image task when references are present.
You can upload up to 16 reference images. JPEG, JPG, PNG, and WEBP files up to 30 MB are supported.
GPT Image 2.5 supports 1K, 2K, and 4K output plus auto, 1:1, 3:2, 2:3, 16:9, 9:16, 4:3, 3:4, 21:9, 27:16, 16:27, 9:8, and 8:9.
The current generator pricing is 6 credits for 1K, 10 credits for 2K, and 16 credits for 4K output.
Use GPT Image 2.5 — Image concepts for controlled image generation, reference-based editing, and high-resolution output.
10,000+ users