A node-graph GUI, API and backend for running diffusion models locally to generate images, video, audio and 3D content.
yang0/handraw-style
A numbered library of 331 hand-drawn illustration styles, 167 layouts and 36 solid color themes that turns picks into bilingual prompts for AI image generators.
- Stars
- 5,795
- Forks
- 666
- Open issues
- 5
- Last commit
- 22 hours ago
What is it?
This project is a prompt library and Skill for AI image generation. It organizes 331 hand-drawn illustration styles, 167 layout templates covering social cards, infographics, comic storyboards, IP characters and e-commerce images, and 36 classic single-color themes. Users pick a style number, layout number and color theme, describe their subject, and receive bilingual English and Chinese prompts to paste into image tools such as Midjourney, DALL-E 3, Stable Diffusion or Flux.
Beyond static prompts, the Skill covers several workflows: recommending a style and color when the user gives only a topic, generating poster prompts, designing article or video covers from a pasted article or subtitle file, planning and batch-inserting illustrations into long Markdown articles, and producing multi-candidate photography session plans with 8-panel prompts. It also distinguishes a pure-illustration mode from a text-and-image mode where lettering is composed into the picture.
The repository includes offline HTML galleries for browsing styles, layouts and colors, and a capability matrix for model-specific behavior. Video production has been split into a separate project.
Key features
- 01Provides 331 numbered hand-drawn styles that can be referenced by code in prompts.
- 02Offers 167 layout templates for social cards, infographics, comic storyboards, IP design and e-commerce.
- 03Includes 36 single-color theme presets with copyable English and Chinese prompt text.
- 04Generates bilingual prompts ready to paste into common image generation tools.
- 05Supports pure-illustration and text-and-image modes for composing lettering into artwork.
- 06Designs article and video covers from pasted text or subtitle files.
Use cases
- Creating social media cover images and illustrated posts with a consistent visual style.
- Planning and generating matching illustrations for a long-form article.
- Drafting comic strips, four-panel stories or storyboard scripts.
- Producing e-commerce main images and detail shots with defined layouts.
Quick start
- 1
Install the skill by sending the repo URL to Codex
- 2
Open the style gallery to browse and pick numbers
- 3
Give the skill a style, layout, color and theme to get bilingual prompts
Things to know
- The license is listed as NOASSERTION, so check the LICENSE file for terms before reuse.
- Output is prompts for external AI image generators, so you need a separate image tool to render images.
Topics
FAQ
- What is handraw-style?
- A numbered library of 331 hand-drawn illustration styles, 167 layouts and 36 solid color themes that turns picks into bilingual prompts for AI image generators. This project is a prompt library and Skill for AI image generation. It organizes 331 hand-drawn illustration styles, 167 layout templates covering social cards, infographics, comic storyboards, IP characters and e-commerce images, and 36 classic single-color themes. Users pick a style number, layout number and color theme, describe their subject, and receive bilingual English and Chinese prompts to paste into image tools such as Midjourney, DALL-E 3, Stable Diffusion or Flux.
- Is handraw-style free to use? What license does it have?
- handraw-style is open source under the Other license. Check the license terms before using it in commercial products.
- Is handraw-style still maintained?
- Actively maintained. The last commit to handraw-style was on Oct 19, 2026.
- What can I use handraw-style for?
- Creating social media cover images and illustrated posts with a consistent visual style. Planning and generating matching illustrations for a long-form article. Drafting comic strips, four-panel stories or storyboard scripts. Producing e-commerce main images and detail shots with defined layouts.
- How do I install handraw-style?
- Install the skill by sending the repo URL to Codex Open the style gallery to browse and pick numbers Give the skill a style, layout, color and theme to get bilingual prompts
- Where can I get handraw-style?
- The source code and installation instructions are on GitHub: https://github.com/yang0/handraw-style
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Offline, open-source image generator built on Stable Diffusion XL that lets you focus on prompts instead of manual parameter tuning.
An AI prompt optimizer that refines prompts, tests and compares their outputs, and saves them as reusable assets, available as web, desktop, Chrome extension, and Docker.
A locally installed, power-user front end for chatting with many LLM APIs, image generators and TTS voice models.
A web-based creative engine for generating and editing images with Stable Diffusion and other AI models, featuring a unified canvas and node-based workflows.
A Claude skill that rewrites rough requests into structured, tool-specific prompts for AI tools such as Claude Code, Cursor, Midjourney and ChatGPT.