Image Models
AI-School uses the central model catalog for text-to-image models. Which models are visible depends on the provider settings of the environment.
Current Catalog
| Provider | Cost-effective | High quality |
|---|---|---|
| OpenAI | GPT Image 1 mini | GPT Image 2 |
| Nano Banana | Nano Banana 2 | |
| Black Forest Labs | FLUX.2 Flex | FLUX.2 Pro Preview |
Nano Banana is the name AI-School uses for Gemini Flash Image models. European image models are provided by Black Forest Labs.
Choosing a Model
| Model | Best for |
|---|---|
| GPT Image 1 mini | Fast concept images, sketches, testing and iteration at lower cost. |
| GPT Image 2 | More polished final images, clearer text in images and more control over finishing. |
| Nano Banana | Fast and affordable images, many variants and simple edits. |
| Nano Banana 2 | Smooth image generation and interactive image editing with Google. |
| FLUX.2 Flex | Flexible European image generation with control, editing and strong quality. |
| FLUX.2 Pro Preview | High-quality European image generation for realistic output and consistent style. |
Format Choices
AI-School shows four general format choices: Automatic, Square, Landscape and Portrait. The central catalog translates these choices to the technical settings required by each provider.
Editing and Inspiration Images
Modern image models can also use images as input. Inspiration images guide style, color or composition. Edit images are source images that the model should change. In edit mode, AI-School does not send a manual aspect ratio, so the source image dimensions can be preserved.
