skillfed

ai-image-generation

Create and edit images using RunComfy's CLI with access to over a dozen AI models including FLUX 2, Google Nano Banana, OpenAI GPT Image 2, ByteDance Seedream, and others. The skill intelligently routes your request to the right model based on your intent—whether you need photoreal portraits, fast iteration, precise typography, or open-weights workflows—and provides the exact command to run.

AI Image Generation lets you create images from text prompts using 11+ models via RunComfy, automatically selecting the best fit for your intent.

AI-generated summary based on this skill's SKILL.md

31 9 MIT updated by prime-skills

Install

prime-skills/runcomfy-agent-skills/ai-image-generation

git clone https://github.com/prime-skills/runcomfy-agent-skills
cp -r runcomfy-agent-skills/ai-image-generation ~/.claude/skills/ai-image-generation
npx skillfed install prime-skills/runcomfy-agent-skills/ai-image-generation

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

How do I generate an image from text with ai-image-generation?

ai-image-generation routes your text prompt to the best-fit AI model from its collection of over a dozen options including FLUX 2, Google Nano Banana, OpenAI GPT Image 2, and ByteDance Seedream. The skill analyzes your intent—whether you need photoreal output, fast iteration, or precise text rendering—and provides the exact RunComfy CLI command to execute your request.

Can ai-image-generation edit or restyle existing images?

Yes. ai-image-generation supports image-to-image editing and restyling workflows. The skill preserves identity and composition while applying AI transformations, intelligently selecting the appropriate model for your editing intent and delivering the RunComfy command needed to transform your image.

What models does ai-image-generation have access to?

ai-image-generation provides access to over a dozen AI models including FLUX 2, Google Nano Banana, OpenAI GPT Image 2, ByteDance Seedream, and others. Each model excels at different tasks—from photoreal portraits and product shots to fast concept generation and precise typography for marketing materials.

Can I create campaign posters with exact in-image text rendering?

Yes. ai-image-generation supports creating campaign posters and marketing visuals with exact text rendering. The skill routes your request to models optimized for typography and branded visuals, then provides the RunComfy CLI command to generate your poster with precise text placement and styling.

How does ai-image-generation handle batch generation for ideation?

ai-image-generation batch-generates concept sketches and moodboards at speed by intelligently selecting fast-iteration models suited to rapid ideation workflows. The skill provides RunComfy commands optimized for quick turnaround, helping you explore multiple creative directions without delays.

What license does ai-image-generation use?

ai-image-generation is released under the MIT license, allowing broad use and modification while maintaining attribution to the original work.

SKILL.md

rendered from the published skill — quoted content, verbatim

AI Image Generation

Generate and edit images with 11+ AI models via the

(truncated - see the full file via the links below)

Read as markdown · JSON record · Browse the source repository

File tree — 1 file
ai-image-generation/SKILL.md

Related skills

Tags

text-to-image image-editing model-routing prompt-optimization batch-generation photoreal-rendering typography-precision multi-reference-conditioning open-weights-models cli-orchestration