TripoGrowthLab/awesome-astra-prompts

200+ Curated GPT-6 Astra prompts and 3D examples for games, Blender scenes and interactive worlds. 14 languages, previews and source links. Updated twice daily. Curated by Tripo.

What it solves

This is a curated collection of GPT-6 Astra prompts for creating 3D games, scenes, and interactive worlds. It saves creators from starting from scratch by giving them ready-to-use prompts that target tools like Blender, Three.js, Unreal Engine, Unity, and the browser.

How it works

Each entry in the list describes a specific prompt, what it builds, who made it, and links to the original post and a detailed view on tripo3d.ai. The prompts cover a wide range — from simple "3D model of a Waymo Jaguar i-Pace using three js" to multi-step agent workflows that direct a model to build Blender meshes, render reference animations, and generate photorealistic videos via PixVerse CLI. Some entries include source code (12 total) and tips or caveats from the authors.

Who it's for

3D creators, game developers, and AI tinkerers who use GPT-6 Astra and want to quickly produce 3D scenes, characters, or interactive web experiences. It's also useful for those exploring prompt-driven workflows that combine multiple tools (Blender, Three.js, video generation).

Highlights

  • 358 example prompts covering games, scenes, models, and interactive demos
  • Available in 14 languages
  • 12 examples include full source code
  • Targets Blender, Three.js, Unreal Engine, Unity, and browser-based projects
  • Each entry links to the original post and a live detail page
  • Includes advanced agent-style prompts (e.g., Blender MCP + PixVerse CLI video workflow)
  • MIT licensed and community-contributed

Related

  • Project
    PozzettiAndrea/ComfyUI-Sharp

    A ComfyUI wrapper for Apple's SHARP model that enables monocular 3D Gaussian Splatting from a single image in under one second.

  • Project
    zju3dv/AutoRecon

    AutoRecon is a research‑grade pipeline that automatically discovers individual objects in a set of RGB images and reconstructs them as neural SDF surfaces, exporting standard mesh files. It combines a coarse object‑decomposition stage (AutoDecomp) with a neural surface reconstruction stage built on nerfstudio/sdfstudio, and provides ready‑to‑run scripts for demo, BlendedMVS, and CO3D datasets.

  • Project
    longxiang-ai/awesome-gaussians

    A curated, automatically updated list of Gaussian Splatting papers and resources, featuring an interactive web atlas, a CLI for searching and exporting references, and topic-based categories to keep researchers current.

  • Project
    inspatio/querysplat

    QuerySplat is a 3D Gaussian Splatting prediction framework that decouples geometry and appearance representations to improve the quality of 3D scene reconstructions from images.