Replicate Prompt Images — prompt skill for prompts by model

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.

Write better image prompts and edits: photographic language, lighting, text rendering, consistent characters.

What it does

Prompting techniques for image generation and editing models on Replicate. It starts by choosing a model through the API rather than from memory, then covers natural-language prompts, camera and lens language, lighting setups, composition, text rendering, style transfer, character consistency and edits such as object removal, background changes, perspective shifts and inpainting.

Use when

Install

Models it drives: nano_banana_pro, flux-2, seedream-5, imagen-4, ideogram, recraft

Example output

https://skills.varg.ai/previews/replicate-prompt-images.webp — Nano Banana Pro output from Replicate's 'How to prompt Nano Banana Pro' guide: a comic-style New York weather report with legible lettering, from its world-knowledge prompting section (credit: Replicate, https://replicate.com/blog/how-to-prompt-nano-banana-pro)

More prompts by model skills