Back to directory

GPT-Image2 Prompt Engine & Template Library

A library of reverse-engineered prompts and reusable templates for GPT-Image 2 and 2.5, browsable on a companion gallery site and packaged as reusable prompt skills for image generation.

GPT-Image2 Prompt Engine & Template Library

The project collects more than 500 reverse-engineered prompt cases and more than 20 template sets for GPT-Image 2, treating prompts as versioned, reusable assets rather than one-off text ("Prompt as Code"). A companion website lets a user browse the gallery, open large previews, copy full prompts, filter by style or scenario, and test generation after signing in, then jump back to the source case on GitHub.

A spotlight section for GPT-Image 2.5 compares two specific model presets side by side using a shared prompt with a draggable divider, including four recreated real-world case images generated without a reference image; the original generation conditions and exact model versions for these recreations are noted as unverified. Selected templates are also packaged as reusable prompt Skills for use in AI coding and agent tools.

It is written in JavaScript and licensed under the MIT license.

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.