Back to directory

AI Visual Prompt Cookbook

AI Visual Prompt Cookbook is a curated, daily-updated library of more than 118 plug-and-play JSON style packs for AI image generation, usable with Nano Banana Pro, GPT Image, Midjourney or any LLM-based image workflow.

AI Visual Prompt Cookbook

AI Visual Prompt Cookbook distills visual design references into structured style.json files, so a visual style can be copied and reused as a self-contained prompt instead of an unstructured piece of text. Each style folder groups a JSON prompt with example variable values, letting a user paste the JSON into ChatGPT, Claude, Nano Banana Pro or another LLM-based image workflow, substitute their own values for the declared variables, and generate an image prompt to send to an image model.

Styles are organized by use case, such as photo-and-doodle social snapshots, zine and collage posters, type-driven campaign graphics, travel and city scenes, editorial and minimal compositions, and product and campaign imagery, with an online gallery for browsing the full catalog.

It is written in Python, curated with the assistance of OpenAI Codex, and licensed under MIT.

More in Generative media

See all 146
  • Blender Copilot

    github.com

    A Copilot-style AI chat panel inside Blender that runs its agent loop in Blender's own Python process, executes the model's generated code against the live scene, and wraps every conversational turn in a single undo step.

  • A ComfyUI add-on that patches ComfyUI-GGUF so Qwen-Image-2.1 models can run fully as GGUF files, fixing a text-encoder mismatch and missing architecture detection until upstream support arrives.

  • A ComfyUI node that expands a short prompt into a full styled prompt, negative prompt and aspect ratio for Qwen-Image-2.1, using one of 17 photographic styles.