Pollinations AI

Generate images, music, and videos from text prompts using Pollinations AI with models like flux, zimage, and suno-4 via API key.

Security Scan

The skill's code and runtime instructions match its stated purpose (image/audio/video generation via Pollinations) and request only the Pollinations API key plus optional Telegram settings; the package is internally coherent with a few minor documentation/metadata mismatches to be aware of.

Purpose & Capability

Name/description match the code: three CLI scripts call Pollinations endpoints to generate images, audio, and video. The only capability that extends beyond pure generation is an optional Telegram send implemented via an 'openclaw message send' subprocess call — the skill does not declare 'openclaw' as a required binary in metadata, so that dependency is undocumented.

Instruction Scope

SKILL.md instructions align with the code: require POLLINATIONS_API_KEY, explain optional TELEGRAM_CHAT_ID, and show how to run the scripts. The scripts only read the declared env vars (POLLINATIONS_API_KEY, TELEGRAM_CHAT_ID, ALLOWED_OUTPUT_DIRS, OPENCLAW_WORKSPACE) and write output files to allowed directories according to sanitizers. No unexpected file reads, secret harvesting, or external endpoints beyond gen.pollinations.ai are present.

Install Mechanism

No install spec is provided (instruction-only install). The included requirements.txt and meta.json list reasonable Python dependencies (requests, Pillow). There are no downloads from arbitrary URLs or archive extraction.

Credentials

Only POLLINATIONS_API_KEY is required (with TELEGRAM_CHAT_ID, ALLOWED_OUTPUT_DIRS, OPENCLAW_WORKSPACE optional). This is proportionate to the stated functionality. The scripts avoid hardcoding secrets and mask the API key in logged URLs.

Persistence & Privilege

The skill does not request permanent 'always' inclusion and does not modify other skills or system-wide settings. It creates output files under a workspace but does not persist credentials or change agent configuration.

Assessment

This skill appears to do what it says: call Pollinations API to generate images, audio, and video. Before installing: (1) only provide a Pollinations API key — avoid giving unrelated secrets; (2) note the optional Telegram feature uses an external 'openclaw' CLI that is not declared in the metadata, so Telegram sending will fail unless you have an appropriate 'openclaw' command installed and trust it; (3) verify ALLOWED_OUTPUT_DIRS and OPENCLAW_WORKSPACE values so generated files are written only where you expect (SKILL.md mentions '/tmp' as a default but the code primarily uses the workspace outputs directory); (4) review network policy if you need to restrict outbound calls to gen.pollinations.ai. If any of the undocumented behaviors (use of 'openclaw' or differences in ALLOWED_OUTPUT_DIRS defaults) are unacceptable, ask the author to update metadata and docs before use.

Pollinations AI - Image, Music & Video Generation

A comprehensive skill for generating images, music, and video using the Pollinations AI API.

Overview

Pollinations.ai provides free AI generation with API key support. This skill enables:

• Image Generation - Create images from text prompts using state-of-the-art models
• Music/Audio Generation - Generate background music and audio tracks
• Video Generation - Create videos from text descriptions

Prerequisites

1. Get an API Key

Visit pollinations.ai to get your free API key.

2. Set Environment Variable

Add to your shell profile (~/.bashrc or ~/.zshrc):

export POLLINATIONS_API_KEY="your_api_key_here"

Then reload:

source ~/.bashrc

3. Install Dependencies

pip install requests Pillow

Security Configuration

Required Environment Variables

Variable	Required	Description
POLLINATIONS_API_KEY	Yes	Your API key from pollinations.ai

Optional Environment Variables

Variable	Default	Description
TELEGRAM_CHAT_ID	(none)	Chat ID for Telegram sending. If not set, --telegram flag is disabled
ALLOWED_OUTPUT_DIRS	., /tmp	Comma-separated list of allowed output directories
OPENCLAW_WORKSPACE	~/.openclaw/workspace	Workspace directory for output files

Note: The --telegram flag requires TELEGRAM_CHAT_ID to be explicitly set. If not set, the feature is disabled for security.

Available Scripts

Script	Purpose
pollinations_image_gen.py	Generate images from text prompts
pollinations_audio_gen.py	Generate music and audio
pollinations_video_gen.py	Generate videos from text

Usage

Image Generation

# Basic usage
python pollinations_image_gen.py "a cute cat" --output cat.jpg

# With specific model and enhancements
python pollinations_image_gen.py "cyberpunk city at night" --model flux --enhance --width 1920 --height 1080 --output city.jpg

# Using different models
python pollinations_image_gen.py "your prompt" --model zimage
python pollinations_image_gen.py "your prompt" --model flux-2-dev  # Free tier

Parameters:

Parameter	Description	Default
prompt	Text description of desired image	(required)
--model	AI model to use	flux
--width	Image width in pixels	1024
--height	Image height in pixels	1024
--enhance	Enable AI prompt enhancement	false
--seed	Fixed random seed for reproducibility	random
--safe	Enable safe mode	false
--output	Output filename	output.jpg
--telegram	Send result via Telegram (requires TELEGRAM_CHAT_ID)	false

Music/Audio Generation

# Generate music from prompt
python pollinations_audio_gen.py "upbeat electronic dance music" --output music.mp3

# With custom duration
python pollinations_audio_gen.py "calm piano melody" --duration 60 --output piano.mp3

Parameters:

Parameter	Description	Default
prompt	Description of desired music	(required)
--model	Audio model	suno-4
--duration	Length in seconds	30
--output	Output filename	output.mp3

Video Generation

# Generate video
python pollinations_video_gen.py "a cat playing with a ball" --output video.mp4

# Custom duration and aspect ratio
python pollinations_video_gen.py "ocean waves" --duration 30 --aspectRatio 16:9 --output ocean.mp4

Parameters:

Parameter	Description	Default
prompt	Description of desired video	(required)
--model	Video model	suno-4
--duration	Length in seconds	10
--aspectRatio	Video aspect ratio (16:9 or 9:16)	16:9
--output	Output filename	output.mp4

Supported Models

Image Models

Model	Description	Quality
flux	Default high-quality model	⭐⭐⭐⭐⭐
flux-2-dev	Latest flux (FREE)	⭐⭐⭐⭐⭐
zimage	Fast generation	⭐⭐⭐⭐
nanobanana	Creative/artistic	⭐⭐⭐⭐
gptimage	OpenAI-based	⭐⭐⭐⭐
seedream	High detail	⭐⭐⭐⭐

Audio Models

Model	Description
suno-4	Latest (recommended) ⭐
suno-3.5	Previous version
suno-3	Legacy model

Video Models

Model	Description
suno	Music video generation ⭐
veo-3.1	Google video AI
seedance	High quality
wan	Open source option
ltx-2	Fast generation

Security Features

This skill includes several security measures:

1. Path Traversal Protection - All output paths are validated against allowed directories
2. Environment Variable Validation - Telegram sending requires explicit opt-in
3. No Hardcoded Credentials - All credentials come from environment variables
4. File Access Whitelist - Only configured directories can be written to

Troubleshooting

Error	Cause	Solution
401 Unauthorized	Missing or invalid API key	Set POLLINATIONS_API_KEY correctly
403 Forbidden	API key lacks permission	Check your key permissions at pollinations.ai
429 Too Many Requests	Rate limit exceeded	Wait before making more requests
402 Payment Required	Insufficient balance	Add credits at pollinations.ai

References

• API Documentation: https://gen.pollinations.ai/api/docs
• Pollinations Website: https://pollinations.ai/