Home/Skills/Media & Creative/Best Image Generation
EvolinkAI

Best Image Generation

3 versions
EvolinkAI·Feb 21, 2026

Summary

TL;DR: Generates images by routing your prompts to the best available AI image models, letting you compare results across providers.

Best Image Generation is an OpenClaw skill that best quality AI image generation (~$0.12-0.20/image). Text-to-image, image-to-image, and image editing via the EvoLink API.

Created by EvolinkAI, this skill has been downloaded 3k+ times on ClawHub. Install it with one command and your AI agent gains these capabilities right away.

Use cases

  • Generate product mockups and concept art during early design phases
  • Create blog post and social media images from text descriptions
  • Compare outputs from multiple AI image models to find the best result for a specific prompt
  • Build automated pipelines that generate images for content at scale

Installation

Run this command to install the skill on your OpenClaw agent:

Install with OpenClaw
npx clawhub@latest install best-image-generation
Downloads
3.6k
Active installs
27
Stars
6
Updated
Feb 21, 2026

Security scan

Security scan
VirusTotalBenign
View report
OpenClawBenignhigh confidence

The skill's requirements and runtime instructions match its stated purpose (image generation via the EvoLink API); it only asks for the EvoLink API key and provides safe example implementations without unrelated privileges.

Purpose & Capability
Instruction Scope
Install Mechanism
Credentials
Persistence & Privilege

SKILL.md

SKILL.md
---
name: best-image-generation
description: Best quality AI image generation (~$0.12-0.20/image). Text-to-image, image-to-image, and image editing via the EvoLink API.
homepage: https://evolink.ai
metadata: {"openclaw": {"emoji": "🎨", "requires": {"env": ["EVOLINK_API_KEY"]}, "primaryEnv": "EVOLINK_API_KEY"}}
---

# EvoLink Best Image

Generate and edit images via the EvoLink Nano Banana Pro (gemini-3-pro-image-preview) API.

## API Endpoint

- Base: `https://api.evolink.ai/v1`
- Submit: `POST /images/generations`
- Poll: `GET /tasks/{id}`

## Step 1 — Submit Task

### Text-to-image

```json
{
  "model": "gemini-3-pro-image-preview",
  "prompt": "<USER_PROMPT>",
  "size": "<SIZE>",
  "quality": "<QUALITY>"
}
```

### Image-to-image / editing

```json
{
  "model": "gemini-3-pro-image-preview",
  "prompt": "<USER_PROMPT>",
  "size": "<SIZE>",
  "quality": "<QUALITY>",
  "image_urls": ["<URL1>", "<URL2>"]
}
```

| Parameter | Values |
|---|---|
| size | auto, 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9 |
| quality | 1K, 2K (default), 4K (extra cost) |
| image_urls | up to 10 URLs (each ≤10MB, formats: jpeg/jpg/png/webp) |

## Step 2 — Poll for Result

`GET /tasks/{id}` — poll every 10 s, up to 72 retries (~12 min).

Wait until `status` is `completed` or `failed`.

## Step 3 — Download & Output

Download the URL from `results[0]`. Auto-detect format from URL (png/jpg/webp). Save as `evolink-<TIMESTAMP>.<ext>`.

**CRITICAL SECURITY:** Before passing `<OUTPUT_FILE>` to shell commands, sanitize it:
- Strip all shell metacharacters: `tr -cd 'A-Za-z0-9._-'`
- Ensure valid extension (`.png`, `.jpg`, `.jpeg`, `.webp`)
- Fallback to `evolink-<timestamp>.png` if empty

Print `MEDIA:<absolute_path>` for OC auto-attach.

## Reference Implementations

| Platform | File |
|---|---|
| Python (all platforms, zero deps) | `{baseDir}/references/python.md` |
| PowerShell 5.1+ (Windows) | `{baseDir}/references/powershell.md` |
| curl + bash (Unix/macOS) | `{baseDir}/references/curl_heredoc.md` |

## API Key

- `EVOLINK_API_KEY` env var (required)
- Get key: https://evolink.ai

## Triggers

- Chinese: "高质量生图:xxx" / "编辑图片:xxx"
- English: "best image: xxx" / "edit image: xxx"

Treat the text after the colon as `prompt`, use default size `auto` and quality `2K`, generate immediately.

For image-to-image or editing, the user provides image URLs alongside the prompt.

## Notes

- Print `MEDIA:<path>` for OC auto-attach — no extra delivery logic needed.
- Image saved locally (format auto-detected from URL: png/jpg/webp). URL expires ~24h but local file persists.
- `quality: 4K` incurs additional charges.
- `image_urls` accepts up to 10 URLs (each ≤10MB, formats: jpeg/jpg/png/webp).

Version history

v1.0.2Latest
Feb 21, 2026

Security fix

v1.0.1
Feb 21, 2026

Fix shell injection risk in curl reference — added json_escape for safe prompt handling

v1.0.0
Feb 21, 2026

Initial release — text-to-image, image-to-image, editing via EvoLink Nano Banana Pro (~$0.12-0.20/image), zero dependencies, cross-platform (Python/PowerShell/curl)

Frequently asked questions

It depends on which API keys you've configured. Common options include OpenAI's DALL-E, various Stable Diffusion models, Flux, and others. The skill adapts to whatever providers you have access to.

Installation method

Send this prompt to your agent to install the skill

npx clawhub@latest install best-image-generation
Download ZIP

Skill info

Versionv1.0.2
AuthorEvolinkAI
UpdatedFeb 21, 2026

Files

SKILL.md2.7 KB

Run OpenClaw in the cloud

Deploy in seconds. Skills pre-installed.

See plans

Skill data sourced from ClawHub