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

> ## Agent Instructions
> Phaseo Gateway base URL: https://api.phaseo.app/v1. Send `Authorization: Bearer $PHASEO_API_KEY` with every request.
> Model IDs look like `provider/model`, for example `openai/gpt-6-astra`. Do not guess IDs: list them with `GET /v1/models` or check https://phaseo.app/models. `phaseo/free` routes to an available free model and needs no wallet balance.
> For new text integrations prefer `POST /v1/responses`. `POST /v1/chat/completions` (OpenAI format) and `POST /v1/messages` (Anthropic format) suit existing code.
> The full API contract is https://phaseo.app/docs/openapi/v1/openapi.yaml. Official SDKs: `@phaseo/sdk` (TypeScript) and `phaseo` (Python), plus Go, C#, PHP, Ruby and Rust.
> Search these docs over MCP at https://phaseo.app/docs/mcp, and install Phaseo skills with `npx skills add https://phaseo.app/docs`. If a page is wrong or out of date, report it with the MCP `submit_feedback` tool.
> Manage Phaseo accounts with the `phaseo` CLI (`npm install -g @phaseo/cli`, then `phaseo login` or `phaseo login --device-code`), the `/v1` Management API or the MCP server at `https://mcp.phaseo.app/mcp?access=manage`. Do not send users to the dashboard for account tasks. A person is still needed for sign-up, approving a sign-in, paying the first top-up on the checkout link that `phaseo credits add` returns when no card is saved, confirming each saved-card top-up from the emailed link, and account security (password, MFA, passkeys). Create API keys with `phaseo keys create --name <name> --json`; never guess one. Credit top-ups need `phaseo login --scopes billing:write` first. Task map: https://phaseo.app/docs/v1/developers/manage-from-an-agent.md.

# Google Nano Banana 2

> What to know when adopting Nano Banana 2 for production image generation and editing.

# Google Nano Banana 2

Use this guide to adopt Nano Banana 2 safely in production image workflows.

Nano Banana 2 is not only a quality upgrade. Google positions it as a production-ready image model with broader control over output format, resolution, and fidelity.

## What's new

* Nano Banana 2 adds explicit control over aspect ratios
* output resolutions now range from `512px` to `4K`
* subject consistency is improved across generations and edits
* instruction following is stronger
* text rendering and translation inside images are better
* visual fidelity is higher while generation remains fast

## Migration quickstart

### 1. Re-check output assumptions

If downstream code assumes a fixed image size, aspect ratio, or crop behavior, update it before rollout. Nano Banana 2 is more flexible, which means older assumptions become easier to violate.

### 2. Update product presets

Revisit:

* social aspect-ratio presets
* default resolution choices
* edit and inpaint workflows
* UI labels that describe available image sizes

### 3. Re-tune prompts for image editing

Because instruction following is stronger, prompts that used to over-specify composition, text, or style may now be unnecessarily rigid. Re-test with shorter prompts and compare results.

## What to test

### Output quality

* vertical, square, and widescreen aspect ratios
* low versus high resolution outputs
* subject consistency across iterative edits
* text rendering, signage, captions, and translated text inside images

### Workflow compatibility

* file handling for larger resolutions
* timeout behavior on higher-fidelity generations
* moderation or human-review pass rate
* downstream resizing and asset-processing assumptions

### Product metrics

* end-to-end generation latency
* usable-output rate
* retry rate
* cost per approved asset

## Rollout advice

1. Split testing by aspect ratio and resolution rather than treating this as a single migration.
2. Validate your asset pipeline on the largest output size you plan to support.
3. Sample real production prompts, especially edits and text-in-image requests.
4. Roll out default preset changes separately from the model swap if your UI exposes image options to users.

## Sources

* [Nano Banana 2](https://blog.google/innovation-and-ai/technology/ai/nano-banana-2/)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.