EverettFish/holo-card-studio

Turn the user's description or uploaded reference into a finished, editable Blender card and an interactive Three.js page. Preserve the requested subject, style, typography and destination. This skill contains code and text only; generated artwork belongs in the user's output project.

What it solves

It enables users to create interactive 3D holographic trading cards from simple text descriptions or images. The project automates the complex process of generating layered artwork, setting up 3D scenes with parallax and holographic effects, and deploying a responsive web viewer for the final result.

How it works

The system operates as a "Codex Skill" that follows a multi-step pipeline:

  1. Layered Generation: It creates four distinct image layers (subject, background, line art, and text) to create a sense of depth.
  2. 3D Scene Construction: It uses Blender to set up parallax, laser-rainbow effects, and starlight textures. The pipeline automatically manages a portable version of Blender to ensure consistency.
  3. Web Deployment: It uses Three.js to reconstruct the 3D composition in a browser, allowing users to rotate, flip, and adjust the holographic shimmer via sliders.
  4. Configuration: A card-config.json file manages metadata like rarity, numbering, and attributes.

Who it’s for

  • Content Creators: For making "legendary" cards of pets, characters, or people for social media.
  • Game Developers: For batch-producing character cards for indie games.
  • HR/Community Managers: For creating unique digital onboarding or anniversary cards for team members.
  • Designers: For experimenting with holographic materials and shaders in Blender.

Highlights

  • Automated Pipeline: Handles everything from image generation to a live Three.js web link.
  • Blender Integration: Provides a fully editable .blend file with Chinese-named node groups for easy material adjustment.
  • Responsive Viewer: The final output is a mobile-friendly web page where users can interact with the card.
  • Customizable Parameters: Users can fine-tune parallax intensity, laser stripe density, and line art glow.

Related

  • Project
    WecoAI/aideml

    AIDE ML is an open‑source Python library that implements an LLM‑guided tree‑search agent for automatically writing, debugging, and optimizing machine‑learning pipelines. Users describe a dataset, a goal, and an evaluation metric in natural language; the agent iteratively generates code, evaluates it, and prunes the search tree until the metric is maximized. The package includes a CLI, a Streamlit UI, HTML visualisation, and works with any OpenAI‑compatible LLM (including local Ollama models).

  • Project
    ATH-MaaS/Ovis

    Ovis is a Multimodal Large Language Model (MLLM) architecture that structurally aligns visual and textual embeddings to enable high-resolution perception and reflective reasoning.

  • Project
    AlekPet/ComfyUI_Custom_Nodes_AlekPet

    A collection of custom nodes for ComfyUI that adds prompt translation, AI-driven content generation, and image manipulation tools.

  • Project
    bytedance/SALMONN

    A suite of advanced multi-modal LLMs that provide large language models with generic hearing abilities and integrated audio-visual perception.