kazusa000/ai_game_workbench

★ 14TypeScriptAudience · designerComplexity · 3/5Setup · moderate

Mindmap

mindmap
  root((ai_game_workbench))
    Modules
      High-res 2D characters
      Pixel art 64x128
    Pipeline
      Generate frames
      Remove background
      Export sprite sheet
    Integrations
      Godot export
      Cloudflare tunnel
    Use cases
      Game animation assets
      Indie game dev
      Prototype characters

mindmap root((ai_game_workbench)) Modules High-res 2D characters Pixel art 64x128 Pipeline Generate frames Remove background Export sprite sheet Integrations Godot export Cloudflare tunnel Use cases Game animation assets Indie game dev Prototype characters

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Generate a 2D character sprite sheet covering walk, idle, run, jump, and attack animations using AI image generation

USE CASE 2

Create pixel-art characters at 64x128 pixels with AI-generated walk cycles and transparent frame exports

USE CASE 3

Export animation assets directly in a format compatible with the Godot game engine

USE CASE 4

Remove green-screen backgrounds from AI-generated frames and preview looped animations before export

Tech stack

TypeScriptNode.jsCloudflare

Getting it running

Difficulty · moderate Time to first run · 30min

Requires your own API keys for image and video generation services, no built-in access is provided.

In plain English

AI Game Workbench is a local desktop tool for creating 2D character animation assets for games using AI image and video generation models. The README is in Chinese. It runs as a local web application: you start it on your own machine, open it in a browser, connect your own API keys for the AI services you want to use, and work from there. No built-in keys are included, so you bring your own access to image and video generation APIs. The tool has two main modules. The first handles high-resolution 2D character creation, covering common animation states like walking, idle, running, jumping, and attacking. For each state it can generate still frames, produce video clips, extract individual frames from those videos, remove green-screen backgrounds, handle looping, and preview the result. It also exports assets in a format compatible with the Godot game engine. The second module handles pixel-art characters at a fixed 64x128 pixel size, with similar steps: generate a base pose, produce a walk cycle, handle chroma keying, slice the sprite sheet, and output individual transparent frames. For video generation to work, the tool needs images accessible via a public HTTPS address. To handle this without requiring a server, the launcher automatically creates a temporary Cloudflare tunnel that exposes your local files to the internet under a randomly assigned URL. The tunnel is only active while the tool is running. On Windows, a prebuilt launcher executable handles startup: it starts the local API server, starts the web frontend, creates the tunnel, and opens the browser. Developers can also run from source using Node.js and npm. API keys are stored in the browser's local storage and never written to the source code or configuration files. All generated images, videos, and exports are saved in a local storage folder on your machine.

Copy-paste prompts

Prompt 1

I want to use ai_game_workbench to generate a walking animation for a fantasy character. What API keys do I need and how do I connect them?

Prompt 2

How do I set up the ai_game_workbench launcher on Windows and generate my first sprite sheet for a 2D platformer?

Prompt 3

Walk me through creating a 64x128 pixel art character with a walk cycle and exporting the frames as transparent PNGs.

Prompt 4

How does ai_game_workbench use a Cloudflare tunnel for video generation and what data does it expose temporarily?

Open on GitHub → Explain another repo

← kazusa000 on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.