image-gen

Generate AI images from text prompts with gpt-image-2 or nano-banana.

751|69|Updated Jun 25, 2026

Search Tags:#image generation #visual assets #ai art #nano-banana #reference images #gpt-image-2

Ready to run

npx skills add https://github.com/ChatCut-Inc/agent-plugin --skill image-gen-chatcut-inc

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: image-gen
Source: https://github.com/ChatCut-Inc/agent-plugin/tree/main/claude/skills/image-gen
Command: npx skills add https://github.com/ChatCut-Inc/agent-plugin --skill image-gen-chatcut-inc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill removes the complexity of creating visual assets by submitting AI image-generation jobs with the right model, composition, quality, and reference-image settings.

Core Features & Use Cases

AI Image Generation: Create images with gpt-image-2 for prompt adherence and readable text, or nano-banana for strong reference-image fidelity.
Flexible Creative Controls: Set aspect ratio, image size, quality where supported, output name, generation count, and project asset references.
Use Case: Generate a 16:9 hero poster, create a background edit using a referenced project image, or produce multiple product visuals for a video project.
Job Tracking: Submit generation jobs and use the progress tracker to monitor non-terminal results.

Quick Start

Use the image generation skill to create a named 16:9 hero poster with gpt-image-2 at the default 1K size.

Frequently Asked Questions about image-gen

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate AI images from text prompts for video project assets?▼

To generate AI images from text prompts, submit a generation job specifying the model, aspect ratio, size, and descriptive asset name. You can produce visual assets like hero posters or product visuals directly for your video projects.

What's the best way to use reference images for background editing and compositing?▼

The best way to use reference images for background editing and compositing is to attach project image references to your generation job. The nano-banana model provides strong reference-image fidelity for matching existing visual assets.

Does gpt-image-2 support readable text generation in AI art?▼

Yes, gpt-image-2 supports readable text generation in AI art. It is specifically recommended for prompt adherence and readable text, making it suitable for poster creation and visual asset production requiring typographic clarity.

Can I output 2K or 4K resolution images for AI art generation?▼

You can output experimental 2K or 4K resolution images for AI art generation, but explicit approval is required. By default, the workflow generates 1K size images at supported aspect ratios unless higher resolutions are explicitly authorized.

Why does my AI image generation job show a non-terminal status?▼

Your AI image generation job shows a non-terminal status because image processing is asynchronous. You must use the progress tracker to monitor non-terminal results until the visual asset generation completes successfully.

How do I track asynchronous AI image generation jobs?▼

You track asynchronous AI image generation jobs by using the built-in progress tracker. After submitting your text prompts and reference settings, monitor the tracker to check job status until the final visual assets are produced.