Vheer Free AI Image Generation Scripts
Scanned 9/5/2026
Install to Claude Code
npx -y skills add dvcrn/openclaw-skills-marketplace --skill vheer-image-generation --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Vheer Image Generation?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/dvcrn-vheer-image-generation)More formats (shields.io, HTML) on the badges page.
---
name: vheer-image-generation
description: "Vheer Free AI Image Generation Scripts"
---
# Vheer Automation Skill
Automated image generation using Vheer.com's browser interface.
## 🌟 Overview
This skill leverages **Playwright** to automate the text-to-image generation process on Vheer.com. It interacts directly with the web interface, avoiding the need for manual cookie management or complex API reverse-engineering.
## 🛠 Features
- **Headless Generation**: Run in the background or in visible mode.
- **Dynamic Prompts**: Pass any prompt via the command line.
- **Automatic Output**: Saves the resulting image directly to your local machine.
- **Persistent Sessions**: Support for User Data Directories to keep you logged in.
## 🚀 Usage
### 1. Installation
Ensure you have the required dependencies installed:
```bash
python3 -m pip install playwright
playwright install chromium
```
### 2. Generating an Image
Run the script with your desired prompt:
```bash
python3 scripts/vheer_automation.py "A majestic phoenix rising from the ashes, cinematic lighting"
```
### 3. CLI Options
- `-o`, `--output`: Specify the output filename (default: `vheer_output.png`).
- `--headful`: Run browser in visible mode (useful for debugging).
- `--user-data`: Path to a browser profile directory (keeps you logged in).
## 📂 Project Structure
- `scripts/vheer_automation.py`: The single, unified automation script.
- `vheer_output.png`: The default location for generated images.
## 💡 How it Works
The script launches a Chromium instance, navigates to the Vheer text-to-image application, fills the prompt textarea, and triggers the generation. Once the "Processing..." state completes, it takes an element-level screenshot of the final image to bypass `blob:` URL limitations.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!