Documentation Index
Fetch the complete documentation index at: https://mintlify.com/anil-matcha/open-generative-ai/llms.txt
Use this file to discover all available pages before exploring further.
Image Studio is the core creative workspace in Open Generative AI, designed around a seamless dual-mode experience. When you open the studio with no reference image, it presents the full roster of 50+ text-to-image models — type a prompt and generate. The moment you upload a reference image, the studio automatically switches to its 55+ image-to-image model set, adapting all controls accordingly. This means you never have to manually toggle between modes: the interface follows your intent based on what you provide.
Dual Mode
Image Studio operates in two distinct modes, switching automatically depending on whether a reference image is present:
| Mode | Trigger | Models | Prompt |
|---|
| Text-to-Image | Default (no image) | 50+ t2i models (Flux, Nano Banana 2, Seedream 5.0, Ideogram, GPT-4o, Midjourney…) | Required |
| Image-to-Image | Reference image uploaded | 55+ i2i models (Kontext, Nano Banana 2 Edit, Seedream 5.0 Edit, Seededit, Upscaler…) | Optional |
Newly Added Models
The following models have been recently added and represent the cutting edge of what Image Studio supports:
| Model | Type | Key Features |
|---|
| Nano Banana 2 | Text-to-Image | Google Gemini 3.1 Flash Image · Resolution 1K/2K/4K · Google Search enhancement · aspect ratio auto |
| Nano Banana 2 Edit | Image-to-Image | Up to 14 reference images · Resolution 1K/2K/4K · Google Search enhancement |
| Seedream 5.0 | Text-to-Image | ByteDance · Quality basic/high · 8 aspect ratios · up to 4K |
| Seedream 5.0 Edit | Image-to-Image | ByteDance · Natural language style transfer · Quality basic/high |
| MiniMax Image 01 | Text-to-Image | MiniMax · 8 aspect ratios · up to 4 images per request · 1500 char prompt |
| Model | Max Images |
|---|
| Nano Banana 2 Edit | 14 |
| Nano Banana Edit | 10 |
| Flux Kontext Dev I2I | 10 |
| Kling O1 Edit Image | 10 |
| GPT-4o Edit / GPT Image 1.5 Edit | 10 |
| Bytedance Seedream Edit v4 / v4.5 | 10 |
| Vidu Q2 Reference to Image | 7 |
| Flux 2 Flex/Pro Edit | 8 |
| Nano Banana Pro Edit | 8 |
| Flux Kontext Pro/Max I2I | 2 |
| Wan 2.5/2.6 Image Edit | 2–3 |
| Qwen Image Edit Plus / 2511 | 3 |
| GPT-4o Image to Image | 5 |
| Flux 2 Klein 4b/9b Edit | 4 |
How the Multi-Select Picker Works
- Checkboxes with order numbers — each selected image displays an order badge; images are sent to the model in the exact order you select them
- Batch upload — the file dialog accepts multiple files at once, adding them all to your upload history in one step
- Count badge — the upload trigger shows how many images are currently active; a
+ badge appears when additional slots are still available for the selected model
- Use Selected button — confirms the current selection and closes the picker, applying the images to the next generation
Controls
Image Studio exposes a set of dynamic controls that adapt to the capabilities of the selected model:
- Aspect Ratio — pick from the aspect ratios supported by the active model (e.g.
1:1, 16:9, 9:16, 4:3, auto)
- Resolution / Quality — visible only for models that expose these options (e.g. 1K/2K/4K for Nano Banana 2, basic/high for Seedream 5.0)
- Seed — set a fixed seed for reproducible outputs; leave at
-1 for random
- Dynamic controls — each model may surface additional parameters specific to its capabilities
Generation History
Every image you generate is automatically saved to muapi_history in localStorage. The history panel lets you browse, revisit, and download all past outputs across sessions — no account or cloud sync required.
Upload History Picker
Every image you upload is stored locally (URL + thumbnail) so you never need to re-upload the same file:
- Click the upload button to open the reference image picker
- Previously uploaded images are displayed in a 3-column grid with thumbnails
- Single-image models — click any thumbnail to instantly select it and close the picker
- Multi-image models — toggle multiple thumbnails (each showing its selection order number), then click Use Selected to confirm
- Add new images at any time with the Upload files button; multi-file selection is supported in multi-image mode
- Remove any image from history with the ✕ button on its thumbnail
- Upload history persists across browser sessions via
localStorage
For the best results with image-to-image models, use a clear, well-lit reference image. The optional prompt lets you describe what you want to change or emphasise — leaving it blank tells the model to infer changes from the image context alone.
