About this model
GPT Image 2 is OpenAI's image generation and editing model, and this entry covers its editing (inpainting) endpoint, exposed as an image-to-image interface. You provide one or more reference images alongside a text prompt, optionally with a mask, and the model applies targeted edits while preserving the parts of the picture you did not specify. It supports both inpainting and outpainting and can draw context from multiple input images. OpenAI describes the line as built for developers needing strong prompt adherence and broad world knowledge.
As the successor to GPT Image 1.5, it sits in the same editing family and pairs with the text-to-image sibling GPT Image 2. A notable change versus the prior generation is fidelity handling: for GPT Image 2 the input fidelity parameter is omitted entirely because the model processes every image input at high fidelity automatically, rather than requiring manual tuning.
The editing variant is reached through the same gpt-image-2 model identifier in OpenAI's API, configured for image-to-image work rather than generation from scratch. This makes it suited to localized retouching, extending canvases, and compositing edits guided by reference imagery.
OpenAI also ships text models like GPT-5.5 and video models in the Sora family, but GPT Image 2 Edit is the dedicated editing tool within that lineup.
This About section is AI-generated from public sources (Claude Opus 4.8), with no human editing. It may contain inaccuracies — verify critical details against the sources listed above.
Data sources: Venice API · HuggingFace · Wikipedia — enrichment updated 13h ago