skills.rest
Aadi-110i
Aadi-110iCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

ai-image-generation

Generate images with 50+ AI models via the inference.sh CLI.

Updated Jul 28, 2026
Search Tags:#image generation#upscaling#text-to-image#ai art#flux#inference.sh#gpt-image
One-click install
npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill ai-image-generation-aadi-110i
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-image-generation
Source: https://github.com/Aadi-110i/PEP-PROJECT/tree/main/skills/ai-image-generation
Command: npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill ai-image-generation-aadi-110i

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Choosing and integrating individual image generation APIs for each model is time-consuming. This Skill provides a single CLI interface to run GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve, and 50+ other image models without writing custom API integrations. ## Core Features & Use Cases - Multi-Model Text-to-Image: Run models like FLUX Dev LoRA, Gemini 3 Pro, Grok Imagine, and Seedream 4.5 through one belt app run command. - Image Editing & Inpainting: Edit existing images with GPT-Image-2 or P-Image-Edit by passing source image URLs alongside prompts. - Upscaling & Stitching: Upscale images with Topaz Upscaler or combine multiple images horizontally or vertically. - Use Case: A marketing designer needs product mockups in 4K. They run Seedream 4.5 with a cinematic prompt, then upscale the result with Topaz, all through the same CLI. ## Quick Start Ask the AI to generate an image of your subject using the FLUX model via the inference.sh belt CLI.

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 FLUX from the command line?▼

Run `belt app run falai/flux-dev-lora --input '{"prompt": "your prompt"}'` after installing and logging into the inference.sh belt CLI. The same pattern works for other models by swapping the app ID.

What AI image models are available through inference.sh?▼

Available models include GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein, Gemini 3 Pro, Grok Imagine, Seedream 4.5, Reve, ImagineArt 1.5 Pro, and P-Image. Run `belt app list --category image` to browse all image apps.

Can I edit an existing image with GPT-Image-2?▼

Yes, GPT-Image-2 supports image editing and inpainting. Pass an `images` array with your source image URL alongside the editing prompt, such as changing the background of a photo.

Which image model is cheapest for bulk generation?▼

FLUX Klein 4B via `pruna/flux-klein-4b` is the most economical option at roughly $0.0001 per image. P-Image is another fast, low-cost choice with multiple aspect ratios.

How do I upscale an AI-generated image to 4K?▼

Use the Topaz Upscaler app with `belt app run falai/topaz-image-upscaler --input '{"image_url": "https://..."}'`. Alternatively, generate natively at 2K-4K with Seedream 4.5 or ImagineArt 1.5 Pro.

Related Skills

Explore More Design & Creative Skills→
agentspace-soagentspace-so
31

flux-kontext

Edit single images with Flux 1 Kontext Pro via RunComfy CLI.

Official
Intermediate
POWERFULMOVESPOWERFULMOVES
1

image-enhancer

Upscale images and sharpen details to reduce compression artifacts.

Community
Basic
ROYCE-8425ROYCE-8425
1

fal-ai-media

Generate images, videos, and audio from text or images via fal.ai MCP.

Community
Advanced
IbIFACE-TechIbIFACE-Tech

provider-integration

Configure and switch between multiple LLM providers like OpenAI, Anthropic, Azure, and Ollama.

Official
Intermediate