skills.rest
brillianodhiya
brillianodhiyaCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

ai-image-generation

Generate and edit images via the RunComfy CLI across multiple AI image models.

Updated Jun 11, 2026
Search Tags:#cli#image generation#Flux#image editing#AI models#text-to-image#runcomfy
One-click install
npx skills add https://github.com/brillianodhiya/VisionScript --skill ai-image-generation-brillianodhiya
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-image-generation
Source: https://github.com/brillianodhiya/VisionScript/tree/main/.agents/skills/ai-image-generation
Command: npx skills add https://github.com/brillianodhiya/VisionScript --skill ai-image-generation-brillianodhiya

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @runcomfy/cli.

What problem does it solve? Choosing the right AI image model and writing correct API calls for text-to-image or image-to-image tasks is tedious and error-prone. This Skill routes each request to the appropriate model on RunComfy and provides the exact CLI invocation and prompting patterns. ## Core Features & Use Cases - Model routing: Picks among FLUX 2, GPT Image 2, Nano Banana 2/Pro, Seedream 5/4-5, Dreamina, Qwen Image, Wan, and Z-Image based on intent such as typography precision, photoreal portraits, or sub-second iteration. - Text-to-image and image-to-image: Covers both t2i generation and i2i editing with documented schemas, prompt tips, and ready-to-run runcomfy run commands. - Use Case: A marketer needs a multilingual poster with an exact Japanese headline. The Skill routes to GPT Image 2, quotes the headline text precisely, and invokes the CLI with the correct size parameter. ## Quick Start Ask the AI to generate an image of your subject, for example a photoreal portrait or a poster with an exact headline, and it will pick the right RunComfy model and run the command.

Frequently Asked Questions about ai-image-generation

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

FAQPage Schema
How do I generate an AI image with the RunComfy CLI?▼

Install the CLI with npm i -g @runcomfy/cli, sign in with runcomfy login, then run runcomfy run <vendor>/<model>/<endpoint> with a JSON --input containing your prompt and an --output-dir for results.

Which AI image model should I use for text in images?▼

GPT Image 2 is the recommended model for in-image text, including Japanese kana, Cyrillic, and Arabic scripts. Quote the exact text in your prompt and name the script for non-Latin languages.

What is the difference between FLUX 2 Klein 9B and 4B?▼

Klein 9B is the default for polished, higher-quality output at around 25 steps. Klein 4B is a sub-second variant suited for storyboards, moodboards, and fast batch concepting with slight quality tradeoff.

Can I edit an existing image with AI models on RunComfy?▼

Yes, image-to-image endpoints like Nano Banana 2 Edit accept 1-20 reference images and preserve identity by default. For mask-driven inpainting, use the dedicated image-edit skill with Z-Image Inpaint.

Why did my RunComfy CLI command fail with exit code 77?▼

Exit code 77 means you are not signed in or the token was rejected. Run runcomfy login interactively, or set the RUNCOMFY_TOKEN environment variable in CI or container environments.

Related Skills

Explore More Design & Creative Skills→
prime-skillsprime-skills
31

flux-2-klein

Generate images with Flux 2 Klein via the RunComfy Model API.

Official
Advanced
cdeistopenedcdeistopened

reel-builder

Generate and animate multi-scene videos from AI stills using Fal.ai, Kling, and ffmpeg.

Community
Advanced
prime-skillsprime-skills
31

image-edit

Route image editing requests to the appropriate RunComfy model and execute them.

Official
Advanced
igniteenowigniteenow
16

comfyui

Generate images, video, and audio by executing ComfyUI diffusion workflows via REST and WebSocket APIs.

Community
Advanced