> For the complete documentation index, see [llms.txt](https://xfigura.gitbook.io/xfigura-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://xfigura.gitbook.io/xfigura-docs/models/image-models/gpt-image-2.md).

# GPT Image 2

High-fidelity image generation and editing for detailed instructions, typography, layouts, and precise changes.

GPT Image 2 is OpenAI's image generation and editing model for high-quality, instruction-led visual work. In xFigura, it is available for text-to-image generation, image editing, and inpainting.

## Example uses

* Infographics, posters, signage, and other visuals containing text
* Dense layouts and multi-part creative briefs
* Product, brand, and editorial assets that require precise direction
* Detailed edits and masked changes to an existing image

## Inputs and outputs

|               | Supported                         |
| ------------- | --------------------------------- |
| Inputs        | Text prompts and reference images |
| Output        | Image                             |
| xFigura modes | Generate, edit, inpaint           |

## Strengths

* Strong instruction following for long or structured prompts
* High-quality typography and layout handling
* High-fidelity use of image inputs for editing
* Flexible image sizes and quality settings at the model level

## Limitations

* Generated text, dimensions, and technical details still require review
* Complex prompts work best when requirements are grouped and prioritized
* Exact controls can differ by mode and may change as the xFigura model catalog is updated

## xFigura tip

Use GPT Image 2 when semantic precision matters as much as visual quality. Put exact copy in quotation marks, describe the layout hierarchy, and separate required elements from stylistic preferences. For a localized change, use the editing or inpainting workflow instead of regenerating the full image.

## Credits and timing

Generation time and credit use depend on the selected mode, output settings, and current model configuration. Review the estimate shown in xFigura before running the job.

## Provider reference

[OpenAI model documentation](https://developers.openai.com/api/docs/models/gpt-image-2)

## Continue

[Compare image models](/xfigura-docs/models/image-models.md)