$npx skillfedfor your agent

Image Generation

Image Generation produces images and videos from text descriptions, defaulting to Google's Gemini for high-quality results or fal.ai FLUX.2 klein 4B in cheap mode for faster, lower-cost output. Customize aspect ratios, resolution, and include reference images for editing. Video generation uses Grok Imagine by default or switches to fal.ai LTX-2 for budget-conscious workflows.

Image Generation creates images from text prompts using Gemini or fal.ai FLUX.2, plus videos with Grok Imagine or LTX-2.

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

★ 44  13 unlicensed, metadata onlyupdated by aviz85

Decision gist · record as of 2026-07-08

Image Generation creates images from text prompts using Gemini or fal.ai FLUX.2, plus videos with Grok Imagine or LTX-2. Image Generation produces images and videos from text descriptions, defaulting to Google's Gemini for high-quality results or fal.ai FLUX.2 klein 4B in cheap mode for faster, lower-cost output. Customize aspect ratios, resolution, and include reference images for editing. Video generation uses Grok Imagine by default or switches to fal.ai LTX-2 for budget-conscious workflows.

manual: git clone https://github.com/aviz85/claude-skills-library → cp -r claude-skills-library ~/.claude/skills/image-generation

Use it when

  • Yes.
  • Image Generation defaults to Google's Gemini for premium quality, but offers fal.ai FLUX.2 klein 4B in cheap mode for faster.
Same gist for agents: .md · .json

Install

aviz85/claude-skills-library/image-generation · repository language: TypeScript

generated, unverified - the skill's exact subdirectory could not be determined; check the repository on GitHub

Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.

Frequently asked questions

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

How do I generate images from text with Image Generation?

Image Generation produces images and videos from text descriptions. By default, it uses Google's Gemini for high-quality results, or you can switch to fal.ai FLUX.2 klein 4B in cheap mode for faster, lower-cost output. Simply provide your text prompt and customize aspect ratios and resolution as needed.

Can Image Generation create pictures with AI without manual design?

Yes. Image Generation automates visual content creation entirely from text prompts, eliminating manual design work. You describe what you want, and the AI generates it. You can also include reference images for editing, giving you control over the output while maintaining automation.

What options does Image Generation offer for faster or cheaper output?

Image Generation defaults to Google's Gemini for premium quality, but offers fal.ai FLUX.2 klein 4B in cheap mode for faster, budget-conscious workflows. For video generation, it uses Grok Imagine by default or switches to fal.ai LTX-2 for cost-effective alternatives.

Can Image Generation produce artwork or graphics quickly for projects?

Image Generation creates artwork and graphics rapidly from text descriptions, making it ideal for quick project needs. It supports bulk content generation for automated image creation at scale, helping you produce visual assets without delays or manual design overhead.

Does Image Generation support video creation from text prompts?

Yes. Image Generation produces both images and videos from text descriptions. Video generation defaults to Grok Imagine for high quality or uses fal.ai LTX-2 for budget-conscious workflows, giving you flexibility in speed and cost.

How can I customize images generated by Image Generation?

Image Generation lets you customize aspect ratios, resolution, and output quality. You can also include reference images to guide the AI's creative direction, giving you control over the final result while maintaining the speed and automation benefits of AI generation.

Let your AI agent find skills like this

Example. Real query, live index.

You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.

wish › “Generate images from text descriptions or prompts”

Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →

Related skills

Nano Banana Poster
by aviz85 · aviz85/claude-skills-library

Nano Banana Poster creates images and posters powered by Google's Gemini model. Choose from five aspect ratios—3:2 horizontal, 1:1 square, 2:3 vertical, 16:9 wide, or 9:16 tall—and optionally include reference assets to guide the generation.

no license declared → metadata onlyupdated Jul 2026
★ 44repo stars
Flux Image
by inference-sh · inference-sh/skills

Flux Image taps FLUX models through the inference.sh CLI to create images from text prompts, image inputs, or custom-styled variations. Choose between high-quality Dev LoRA for production work or the faster Klein variant for rapid iteration.

no license declared → metadata onlyupdated Jul 2026
★ 660repo stars
fal-model-guide
by JosiahSiegel · JosiahSiegel/claude-plugin-marketplace

fal-model-guide helps you navigate fal.ai's model catalog by comparing FLUX, Stable Diffusion, Kling, LTX, and audio models across performance tiers. It provides side-by-side quality, speed, and pricing comparisons to match your use case—whether you need production-grade output, fast iteration, or cost optimization.

MITupdated Jun 2026
★ 49repo stars
Fal Regenerate 3d
by fal-ai-community · fal-ai-community/skills

Fal Regenerate 3d orchestrates a complete pipeline for shipping polished multi-character 3D web experiences using fal.ai models. It generates rigged animated character GLBs, companion creatures, PBR floor textures, looped video backgrounds, and bundles them into a static Three.js scene with palette swaps, reflections, and transition effects. Visitors with a FAL key can also generate custom characters live in-browser.

no license declared → metadata onlyupdated May 2026
★ 218repo stars
happy-image-gen
by iamzhihuix · iamzhihuix/happy-claude-skills

happy-image-gen unifies image generation across eight providers—OpenAI, Google, Replicate, Stability AI, FAL, Ark, Bailian, and SiliconFlow—under a single command-line interface. Create still images from text prompts or transform existing images with reference-driven edits. The skill auto-detects available API keys and respects your configuration defaults, so you can switch providers without rewriting commands.

MITupdated Apr 2026
★ 305repo stars
Inno Figure Gen
by OpenLAIR · OpenLAIR/dr-claw

Create or modify images by specifying a prompt and choosing your resolution tier. The skill defaults to OpenAI's image model when available, seamlessly switching to Gemini if needed. Control output size, pick your provider, and iterate quickly from draft to final.

no license declared → metadata onlyupdated Jul 2026
★ 1,038repo stars
Tags
ai-artvisual-synthesisprompt-basedcontent-creationautomationcreative-toolsneural-renderingasset-generation