helloianneo/ian-handdrawn-ppt

中文手绘技术 PPT 整页图像生成 Skill | 21:9 封面 + 16:9 正文配图 | PNG 输出

What it solves

It transforms text-based materials—such as articles, course notes, outlines, or existing documents—into a series of hand-drawn, technical explanation images in a PPT-style format. It solves the problem of creating visually appealing, non-generic technical illustrations and knowledge cards that avoid the "template PPT look" while maintaining a consistent visual style across multiple pages.

How it works

This project is a Codex Skill that guides an AI Agent through a structured workflow to generate raster images (PNGs) rather than editable presentation files. The process involves:

  1. Content Analysis: Reading the source material to determine the theme, audience, and core arguments.
  2. Narrative Planning: Organizing the content into a narrative structure (e.g., teaching, persuasion, or product explanation).
  3. Layout Selection: Mapping content to specific page archetypes like metaphors, comparisons, flows, or matrices.
  4. Visual Styling: Applying a consistent "visual DNA" (near-white backgrounds, thin hand-drawn lines, and a specific muted color palette).
  5. Image Generation: Writing detailed prompts for an image model (preferably ChatGPT Image 2.0) to produce 21:9 cover images and 16:9 body images.

Who it’s for

  • Technical writers and educators who need cover images and illustrations for Chinese technical articles or courses.
  • Content creators who want to turn long-form text or outlines into visual knowledge cards.
  • Users of Codex who want AI to plan the narrative flow before generating images.

Highlights

  • Narrative-First Approach: Focuses on content structure and semantic layout before image generation.
  • Consistent Visual Identity: Enforces a specific hand-drawn aesthetic with muted colors and minimal clutter.
  • Specific Output Formats: Generates 21:9 covers and 16:9 body images as PNGs.
  • Integrated Workflow: Includes a full pipeline from intake and narrative planning to prompt engineering and quality checking.

Related

  • Project
    scraed/LanPaint

    A training-free universal inpainting sampler for ComfyUI that enables high-quality image, video, and audio inpainting across almost any pretrained diffusion model.

  • Project
    liangdabiao/ecom-details-image

    The ecom‑details‑image skill is a CLI‑based tool that creates complete e‑commerce visual packages (main images, detail‑page graphics, banners, etc.) using AI image models via the apiz service or Codex’s built‑in imagegen. It can output a structured visual brief and prompt, or directly generate images, applying a “Campaign Style Lock” to keep style consistent across the set. Installation requires the apiz CLI; usage is driven by prompts to an AI assistant or by running `scripts/generate_image.py` with options for prompt source, size, model, and reference images. The repo contains no API keys and warns about cost, async generation, and compliance with content policies.

  • Project
    morsoli/aimangastudio

    An AI-powered comic creation tool that provides an end-to-end pipeline for script generation, storyboarding, and character style control.

  • Project
    NO6KIKO/gorest-2d-animation-spritesheet-generator

    Gorest is a Node‑based, browser‑run editor that lets you build 2‑D game scenes, generate or import spritesheets, attach rich metadata, and preview animations—all with optional Codex‑driven prompts. It stores assets locally and includes a fake‑3D rotator for turntable‑style sprites.