AI Image Generation — model skill for images & thumbnails

For AI agents: find the right skill in one call — curl -s "https://skills.varg.ai/api/search?q=<what the person wants>" returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the use-case page.

Generate images with 50+ models from one CLI: GPT Image 2.5, FLUX, Gemini, Grok, Seedream, Reve and more.

What it does

inference.sh's router skill for image generation through the belt CLI, with one command shape (belt app run <app>) across 50+ models. It covers GPT Image 2.5, FLUX, Gemini image models, Grok Imagine, Seedream, Reve and P-Image, with guidance on which one to pick for a job.

Use when

Install

Models it drives: gpt_image_2_5, gpt_image_2, flux_dev, nano_banana_pro, grok_imagine_image, seedream, p-image

Example output

https://skills.varg.ai/previews/inference-sh-ai-image-generation.webp — gpt-image-2 text-to-image output from OpenAI's prompting guide (GPT-Image is the skill's default family): a photoreal 35mm-style candid of an old sailor mending a net with his dog on deck (credit: OpenAI Cookbook (gpt-image-2 output), https://github.com/openai/openai-cookbook/blob/main/examples/multimodal/image-gen-models-prompting-guide.ipynb)

More images & thumbnails skills

Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.