Back to directory

Awesome GPT Image 2 Prompts

A curated collection of 462 example prompts for OpenAI's GPT Image 2 model, organized by category for image generation, editing, design and advertising work, each with attribution to its original source.

Awesome GPT Image 2 Prompts

This repository is a prompt-first library of 462 curated examples for GPT Image 2, OpenAI's image generation and editing model, covering image generation, editing, design, advertising and visual experimentation. Prompts are organized by category, keep their original source and creator attribution where available, and can be copied and adapted to a new image.

GPT Image 2 supports text-to-image generation, image editing such as inpainting, outpainting and style transfer, multi-turn refinement through dialogue, high-fidelity text rendering inside generated images, and consistent character identity across multiple generations, through a single API call for both generation and editing.

The project is updated with new prompt cases regularly after a review and validation pass, and is released under the CC0-1.0 public domain dedication.

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.