🎨 Pollinations Image Generation Skill

A clean, modular, and user-friendly image generation tool powered by [Pollinations.ai](https://pollinations.ai).

3,891 stars

Best use case

🎨 Pollinations Image Generation Skill is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

A clean, modular, and user-friendly image generation tool powered by [Pollinations.ai](https://pollinations.ai).

Teams using 🎨 Pollinations Image Generation Skill should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/pollinations-image/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/aprilox/pollinations-image/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/pollinations-image/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How 🎨 Pollinations Image Generation Skill Compares

Feature / Agent🎨 Pollinations Image Generation SkillStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

A clean, modular, and user-friendly image generation tool powered by [Pollinations.ai](https://pollinations.ai).

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# 🎨 Pollinations Image Generation Skill

A clean, modular, and user-friendly image generation tool powered by [Pollinations.ai](https://pollinations.ai).

## ✨ Features

- 🎁 **5,000 free images/month** with pollen grants
- 🔄 **Easy model switching** - change anytime
- 💾 **Persistent defaults** - remember your preferences
- 📊 **Clear model comparison** - quality, speed, cost
- 🔧 **Modular design** - easy to extend

## 🚀 Quick Start

### First Time Setup

```bash
# 1. Clone or copy the skill
cd pollinations-image/

# 2. (Optional) Configure your API key
cp .env.example .env
# Edit .env and add your key from https://enter.pollinations.ai

# 3. (Optional) Set your default model  
cp .user.conf.example .user.conf
# Edit .user.conf to change DEFAULT_IMAGE_MODEL

# 4. List all available models
./generate.sh models

# 5. Generate your first image
./generate.sh "a cute purple cat"
```

### Already Configured?

```bash
# List all available models
./generate.sh models

# Set your default model (optional)
./generate.sh set-model flux

# Generate an image
./generate.sh generate --prompt "a cute purple cat"

# Or use the shortcut
./generate.sh "a cute purple cat"
```

## 📋 Available Models

| Model | Type | Speed | Quality | Cost |
|-------|------|-------|---------|------|
| `flux` | 🎁 Free | ⚡⚡ | ⭐⭐⭐⭐⭐ | ~0.0002 pollen/img |
| `zimage` | 🎁 Free | ⚡ | ⭐⭐⭐⭐ | ~0.0002 pollen/img |
| `klein` | 💰 Paid | ⚡⚡ | ⭐⭐⭐⭐⭐ | ~0.008 pollen/img |
| `klein-large` | 💰 Paid | ⚡⚡⚡ | ⭐⭐⭐⭐⭐⭐ | ~0.012 pollen/img |
| `gptimage` | 💰 Paid | ⚡⚡ | ⭐⭐⭐⭐⭐ | 2.0-8.0 pollen/M |

## 📖 Commands

### `generate` (or `g`)
Generate an image with your prompt.

```bash
# Full command
./generate.sh generate --prompt "a sunset over mountains" --model flux --width 1024 --height 1024

# Short options
./generate.sh g -p "a sunset" -m zimage -w 512 -h 512

# Even shorter (prompt only)
./generate.sh "a cute cat"
```

**Options:**
- `--prompt, -p` - Image description (required)
- `--model, -m` - Model to use (overrides default)
- `--width, -w` - Image width (default: 1024)
- `--height, -h` - Image height (default: 1024)
- `--seed, -s` - Random seed for reproducibility
- `--filename, -f` - Custom output filename
- `--nologo` - Remove Pollinations watermark
- `--enhance` - Let AI improve your prompt

### `models` (or `m`)
Display all available models with ratings.

```bash
./generate.sh models
```

### `model MODEL_NAME`
Show detailed information about a specific model.

```bash
./generate.sh model klein-large
```

### `set-model MODEL_NAME`
Set your default model for all future generations.

```bash
./generate.sh set-model zimage
```

**Note:** This saves to `.user.conf` and persists across sessions.

### `config`
Display your current configuration.

```bash
./generate.sh config
```

### `help`
Show help message.

```bash
./generate.sh help
```

## ⚙️ Configuration

User preferences are stored in `.user.conf`:

```bash
# Example .user.conf
DEFAULT_IMAGE_MODEL=flux
```

API keys are stored in `.env` (not tracked in git):

```bash
# Example .env
POLLINATIONS_API_KEY=your_key_here
```

## 📁 Structure

```
pollinations-image/
├── generate.sh        # Main entry point
├── lib/
│   └── models.sh      # Model registry and metadata
├── .env               # API keys (private)
├── .user.conf         # User preferences
└── SKILL.md           # This documentation
```

## 🎯 Recommended Workflows

### Draft → Refine → Final

```bash
# 1. Quick draft with fast model
./generate.sh g -p "concept sketch of a dragon" -m zimage -w 512

# 2. Refine with better model
./generate.sh g -p "detailed dragon in a castle" -m flux -w 1024

# 3. Final high-quality render
./generate.sh g -p "masterpiece, highly detailed dragon..." -m klein-large
```

### Daily Driver Setup

```bash
# Set fast model for daily use
./generate.sh set-model zimage

# All future generations use zimage by default
./generate.sh "quick concept"

# Override for special occasion
./generate.sh "important artwork" --model klein-large
```

## 🔑 Getting an API Key

1. Visit [enter.pollinations.ai](https://enter.pollinations.ai)
2. Create an account
3. Request a pollen grant (free tier: 5K images/month)
4. Generate an API key
5. Save it to `.env`: `POLLINATIONS_API_KEY=your_key`

## 🤝 Contributing & Sharing

This skill is designed to be shared! 

### Files to Include

When sharing the skill, include:
- ✅ `generate.sh` — Main script
- ✅ `lib/models.sh` — Model registry
- ✅ `.env.example` — Example API key file
- ✅ `.user.conf.example` — Example user config
- ✅ `SKILL.md` — Documentation

### Files to Exclude (Private)

Do NOT share these (they contain personal data):
- ❌ `.env` — Your private API key
- ❌ `.user.conf` — Your personal preferences
- ❌ `.first-run-complete` — Setup marker

### Adding a New Model

1. Edit `lib/models.sh`
2. Add your model to `MODELS_LIST` following the format:
   ```
   model_id|Display Name|type|cost|speed|quality|Description
   ```
3. Test with `./generate.sh model your_model_id`

### First-Time User Experience

When someone first runs the skill without config files, they'll see a welcome message guiding them through setup. The skill works out-of-the-box with sensible defaults:
- **Default model:** `flux` (free, high quality)
- **API key:** Optional (works with public endpoint)
## 📝 License

MIT - Feel free to use, modify, and share!

---

Made with 🫐 for the OpenClaw community.

Related Skills

alphashop-image

3891
from openclaw/skills

AlphaShop(遨虾)图像处理 API 工具集。支持11个接口:图片翻译、图片翻译PRO、 图片高清放大、图片主题抠图、图片元素识别、图片元素智能消除、图像裁剪、 虚拟试衣(创建+查询)、模特换肤(创建+查询)。 触发场景:图片翻译、翻译图片文字、放大图片、高清放大、抠图、去背景、 检测水印/Logo/文字、消除水印、去牛皮癣、裁剪图片、虚拟试衣、AI试衣、 模特换肤、换模特、AlphaShop图像、遨虾图片处理。

Image Processing & Analysis

image-gen

3891
from openclaw/skills

Generate AI images from text prompts. Triggers on: "生成图片", "画一张", "AI图", "generate image", "配图", "create picture", "draw", "visualize", "generate an image".

Content & Documentation

minimax-imagegen

3891
from openclaw/skills

Expert image generation skill using MiniMax image-01. Use this skill ANY TIME the user asks to create, generate, make, or produce an image, visual, graphic, banner, illustration, icon, screenshot mockup, hero image, thumbnail, social media asset, app icon, website visual, or any other image — even if they just say "make me a picture of X." This skill should also trigger when the user asks to improve or iterate on a previous image prompt, or when image output would enhance a task (e.g., "I need a hero image for my blog post"). Covers all use cases: website assets for tonyreviewsthings.com and tonysimons.dev, app/software media, marketing visuals, social media content, UI mockups, character/portrait generation, and general creative requests.

image-to-editable-ppt-slide

3891
from openclaw/skills

Rebuild one or more reference images as visually matching editable PowerPoint slides using native shapes, text, fills, and layout instead of a flat screenshot. Use when the user wants an image, flowchart, infographic, dashboard, process diagram, or designed slide converted into an editable PPT/PPTX deck that stays editable and closely matches the source.

openrouter-image-generation

3891
from openclaw/skills

Generate or edit images through OpenRouter's multimodal image generation endpoint (`/api/v1/chat/completions`) using OpenRouter-compatible image models. Use for text-to-image or image-to-image requests when the user wants OpenRouter, `OPENROUTER_API_KEY`, model overrides, or provider-specific `image_config` options.

PDF Generation Skill

3891
from openclaw/skills

**Purpose:** Generate professional PDFs from HTML/CSS without whitespace gaps or layout issues.

save-article-with-images

3891
from openclaw/skills

Save web articles locally with images. Automatically downloads images, generates Markdown, and converts to PDF. Supports WeChat Official Account articles via subagent isolation. Triggers: save article, save this article, download article, clip article, wechat article.

blog-image-claw-skill

3891
from openclaw/skills

Generate ai blog image generator images with AI via the Neta AI image generation API (free trial at neta.art/open).

image-review

3891
from openclaw/skills

用户说评价、改进、优化图片时触发。

generate-image

3891
from openclaw/skills

用户请求画图时触发。

modelscope-image-gen

3891
from openclaw/skills

通过魔搭社区(ModelScope) API 生成图片。先使用 --list-models 查看可用模型,然后根据用户需求由 AI 生成专业的提示词,最后调用 API 生成图片。支持 Kolors、Stable Diffusion XL、FLUX 等多种文生图模型。当用户需要使用魔搭社区、ModelScope 或中文 AI 模型生成图片时使用此技能。

keevx-image-to-video

3891
from openclaw/skills

Use the Keevx API to convert images to videos. Supports multiple models (V/KL), various resolutions (720p/1080p/4K), and audio generation. Use this skill when the user needs to: (1) Convert images to video (2) Generate video with Keevx (3) Create and query image-to-video tasks (4) Batch image-to-video conversion. Keywords: image to video, Keevx, video generation.