How should WaveSpeedAI Nano Banana Pro Image Generation/Editing be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

WaveSpeedAI Nano Banana Pro Image Generation/Editing

Generate and edit images using Google's Nano Banana Pro model via WaveSpeed AI. Supports text-to-image generation and image editing with natural language prompts. Features native 4K resolution, flexible aspect ratios, multilingual text rendering, and camera-style controls. Use when the user wants to create images from text or edit existing images.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.5k

Updated

Oct 10, 2026

Version

2.0.1

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.5K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.5K downloadsadoption · observed Oct 10, 2026
Latest release: 2.0.1release · observed Sep 5, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17epnq4kcsv1261rq3e9gvwcx8dth5q:wavespeed-nano-banana-pro

Install using `clawhub skill install s17epnq4kcsv1261rq3e9gvwcx8dth5q:wavespeed-nano-banana-pro` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/wavespeed/wavespeed-nano-banana-pro before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-wavespeed-wavespeed-nano-banana-pro/snapshot"

Documentation

CLAWHUB

32,031 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: wavespeed-nano-banana-pro
description: Generate and edit images using Google's Nano Banana Pro model via WaveSpeed AI. Supports text-to-image generation and image editing with natural language prompts. Features native 4K resolution, flexible aspect ratios, multilingual text rendering, and camera-style controls. Use when the user wants to create images from text or edit existing images.
metadata:
  author: wavespeedai
  version: "2.0"
---

# WaveSpeedAI Nano Banana Pro Image Generation/Editing

Generate and edit images using Google's Nano Banana Pro model via the WaveSpeed AI platform. Supports both text-to-image generation and natural-language image editing with up to 14 input images.

## Setup

Install the open-source CLI once and sign in; the CLI stores the key, so never ask the user to paste an API key into the chat:

```bash
npm install -g @wavespeed/cli
wavespeed login          # opens https://wavespeed.ai/accesskey and stores the key
wavespeed status         # confirms you are signed in
```

For CI or one-off shells, `WAVESPEED_API_KEY` in the environment also works.

Prefer MCP tools over shell commands? The same platform is exposed by [`@wavespeed/mcp`](https://github.com/WaveSpeedAI/mcp-server) (`npx -y @wavespeed/mcp`; tools `search_models`, `get_model_schema`, `get_price`, `upload_file`, `run_model`, `get_prediction`). It shares the CLI's stored login. Every example below maps one-to-one onto `run_model` with the same model id and input fields.

## Quick Start

### Text-to-Image

```bash
OUTPUT_URL=$(wavespeed run google/nano-banana-pro/text-to-image \
  -p "A serene Japanese garden with cherry blossoms, watercolor style" \
  --json | jq -r '.outputs[0]')
```

### Image Editing

The `images` parameter accepts an array of image URLs. For local files use the `@path` marker; the CLI uploads them for you.

```bash
# Upload a local image to get a URL
OUTPUT_URL=$(wavespeed run google/nano-banana-pro/edit \
  -i images='["@./photo.png"]' \
  -p "Replace the sky with a dramatic sunset" \
  --json | jq -r '.outputs[0]')
```

Existing URLs work as-is:

```bash
OUTPUT_URL=$(wavespeed run google/nano-banana-pro/edit \
  -i images='["https://example.com/photo.jpg"]' \
  -p "Replace the sky with a dramatic sunset" \
  --json | jq -r '.outputs[0]')
```

## API Endpoints

### Text-to-Image

**Model ID:** `google/nano-banana-pro/text-to-image`

Generate images from text prompts.

#### Parameters

| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `prompt` | string | Yes | -- | Text description of the image to generate |
| `aspect_ratio` | string | No | -- | Output aspect ratio. One of: `1:1`, `3:2`, `2:3`, `3:4`, `4:3`, `4:5`, `5:4`, `9:16`, `16:9`, `21:9` |
| `resolution` | string | No | `1k` | Image resolution. One of: `1k`, `2k`, `4k` |
| `output_format` | string | No | `png` | Output format. One of: `png`, `jpeg` |

#### Example

```bash
OUTPUT_URL=$(wavespeed run google/nano

_meta.json

{
  "ownerId": "kn733k72mbe41a710dd1kfpg2s8257bs",
  "slug": "wavespeed-nano-banana-pro",
  "version": "2.0.1",
  "publishedAt": 1788625709043
}

skill-card.md

## Description:

Generate and edit images with Google's Nano Banana Pro model through WaveSpeed AI, including text-to-image prompts, natural-language edits, flexible aspect ratios, 1k/2k/4k outputs, and PNG/JPEG output.

This skill is ready for commercial/non-commercial use.

## Publisher:

[wavespeed](https://clawhub.ai/user/wavespeed)

### License/Terms of Use:

MIT-0

## Use Case:

External users and developers use this skill to direct an agent through WaveSpeed AI setup and Nano Banana Pro image generation or image-editing runs. It is suited for creating new images from prompts, editing user-provided images, choosing output formats, and saving generated results.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill uses a paid remote service and uploads prompts plus any selected local images.

Mitigation: Confirm user intent before uploads, pass only user-provided media or prior result URLs, and avoid sending sensitive prompts or images unless the user accepts the remote-service exposure.

Risk: The setup path can rely on global npm installation or ad hoc npx execution for WaveSpeed tooling.

Mitigation: Install WaveSpeed tooling only from trusted sources, prefer pinned package versions or a project-local locked install, and avoid ad hoc npx -y execution when possible.

Risk: Stored WaveSpeed credentials could be misused if local tooling or dependencies are compromised.

Mitigation: Keep WaveSpeed credentials out of chat and rotate the stored credential if dependency compromise is suspected.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/wavespeed/skills/wavespeed-nano-banana-pro)
- [WaveSpeed MCP server](https://github.com/WaveSpeedAI/mcp-server)
- [WaveSpeed access key page](https://wavespeed.ai/accesskey)

## Skill Output:

**Output Type(s):** [Shell commands, Configuration, Guidance, API calls, Files]

**Output Format:** [Markdown with bash command examples, parameter tables, and usage guidance]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [When commands are executed, WaveSpeed returns prediction metadata, image URLs, and optionally downloaded PNG or JPEG image files.]

## Skill Version(s):

2.0.1 (source: server release evidence; SKILL.md frontmatter lists 2.0)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 17h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular