> ## Documentation Index
> Fetch the complete documentation index at: https://docs.lovable.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Let users generate and edit images in your app

> Add image generation and editing to your app. For detailed edits, fast previews, and short animated GIFs.

Image models generate and edit images from text prompts, uploaded images, or both. Use them for visual assets, product mockups, marketing imagery, and in-app image editing.

Ask Lovable to:

* Generate images from a text description.
* Edit or restyle an uploaded image.
* Create product mockups or marketing visuals.
* Produce thumbnails or illustrations on demand.
* Turn one product photo into a full set of product images.

Ask for any of these in the project chat, and Lovable writes the feature and the backend call behind it. See [Add an AI feature to your app](https://docs.lovable.dev/features/ai#add-an-ai-feature-to-your-app) for the whole flow, including publishing.

| Model | Best for |
| - | - |
| [GPT Image 2.5 Sunburst (default)](https://platform.openai.com/docs/models/gpt-image-2.5-sunburst) | Highest-quality image generation and editing when output quality or editing precision matters most, such as final assets and detailed visuals. |
| [GPT Image 2.6 Sunburst](https://developers.openai.com/api/docs/models/gpt-image-2.6-sunburst) | Detailed visuals and precise edits. Also generates short animated GIFs. |
| [GPT Image 2.6 Flare](https://developers.openai.com/api/docs/models/gpt-image-2.6-flare) | Fast generation and editing for previews and in-app image editors. Also generates short animated GIFs. |
| [GPT Image 2](https://platform.openai.com/docs/models/gpt-image-2) | High-quality image generation and editing for product mockups, marketing imagery, and creative content. |
| [GPT Image 2.5 Flare](https://platform.openai.com/docs/models/gpt-image-2.5-flare) | Fast image generation and editing when response time matters most, such as previews and in-app image editors. |
| [Gemini 3.1 Flash Lite Image](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-1-flash-lite-image) | Faster, lower-cost image generation and editing for high-volume, cost-sensitive workflows. Also known as Nano Banana 2 Lite. |
| [Gemini 3 Pro Image](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-pro-image) | Detailed visuals, text rendering in images, and multi-image composition. Also known as Nano Banana Pro. |
| [Seedream 5 Pro](https://developers.cloudflare.com/ai/models/bytedance/seedream-5-pro/) | Posters, ads, and designs built from several reference images, with accurate text rendering inside the image. Takes up to 10 reference images in one request and returns one image. Available after an admin or owner enables **ByteDance** in [Connectors](https://lovable.dev/dashboard?connectors). |

All the image models above can edit an uploaded image as well as generate new ones. Describe the change you want.

With the GPT Image models you can also limit the edit to a selected area of the image (a mask). Those models can produce images with a transparent background, as PNG or WebP files.

When you ask Lovable to add image generation to your app, you can ask for a speed or quality level instead of a specific model: fast, standard, or premium.

Lovable picks the model for each level and updates it as better models become available.

## Use GPT Image 2.6

**GPT Image 2.6 Flare** and **GPT Image 2.6 Sunburst** generate and edit images from a text prompt, an uploaded image, or both. **GPT Image 2.6 Flare** is the faster model, for previews and in-app image editors. **GPT Image 2.6 Sunburst** is for detailed visuals and precise edits.

Ask Lovable to use **GPT Image 2.6 Flare** or **GPT Image 2.6 Sunburst**. Fast, standard, and premium still use the models Lovable picks for those levels.

Both models can produce a still image with a transparent background, as a PNG or WebP file. Your app can limit an edit of a still image to a selected area.

**GPT Image 2.6 Flare** and **GPT Image 2.6 Sunburst** can produce a short animated GIF. A GIF has 2 to 16 frames. When you do not ask for a length, the GIF has 9 frames, and each frame stays on screen for 200 milliseconds. A GIF edit cannot be limited to a selected area.

Your app can guide an edit with a drawing on a transparent layer that is the same size as the image. The drawing shows where the change goes, and the prompt says what the change is. An edit uses either that layer or a selected area of the image.

Complexity is how much the model plans before it renders the image. Ask Lovable to set complexity to low, medium, or high. Quality controls how much visual detail the image has. Both models use high complexity when you do not ask for a level.

**GPT Image 2.6 Flare** and **GPT Image 2.6 Sunburst** do not produce SVG files. Ask for a PNG, JPEG, or WebP file, or for an animated GIF.

**GPT Image 2.6 Flare** and **GPT Image 2.6 Sunburst** are not available while [EU inference](https://docs.lovable.dev/features/eu-inference.md) is enabled. A request for either model fails with an error.
