# LigphiDonk/academic-figure-generator

AI 驱动的学术论文配图生成平台。上传论文 → AI 分析内容生成 Prompt → 一键生成高质量科研配图，还有配套的skill可在主流agent中使用

Repository: https://github.com/LigphiDonk/academic-figure-generator
Canonical: https://ross.abutalabs.com/products/academic-figure-generator
Language: Python
License: MIT
License Family: permissive
Last push: 2026-03-27T03:01:07+00:00

## Health v2 (maintenance only)
Score: 62/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 74, release rhythm 74, longevity 13
- inputs: {"age_days": 185, "days_push": 159, "days_rel": 172, "gap_med": 5, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2190, forks 113 (observed 2026-08-28T04:06:24.054875+00:00)

## What it is
A self-hosted AI-powered platform that generates high-quality academic paper figures: users upload a paper (PDF/DOCX/TXT), Claude analyzes the content to produce image prompts, and NanoBanana/Gemini renders the figure. Built with a FastAPI backend and React 19 frontend, it also ships a skill for use in mainstream AI agents.

## Use cases
- generate figures for academic papers from pdf
- create scientific diagrams with ai
- turn my research paper into architecture diagrams
- generate publication-ready illustrations from a manuscript
- make colorblind-friendly academic figures
- edit generated figures with text instructions
- produce deep learning module diagrams for a paper

## When to choose
- you need publication-quality figures for papers without manual drawing
- you want a local, self-hosted tool with project management for papers and figures
- you need multiple resolutions, aspect ratios, and academic color schemes including colorblind-friendly palettes
- you want AI to read your paper and draft figure prompts automatically

## When to avoid
- you need precise, editable vector diagrams with exact layout control
- you require offline operation without API keys for Claude or Gemini
- you want a fully managed cloud service rather than a local deployment
- your figures must be generated from structured data like charts or plots

## Facets
- artifact type: application
- maturity: active
- function: llm-inference, image-processing, rag, pdf, web-framework, api-framework
- domain: artificial-intelligence, large-language-models, image-processing, pdf, education, web-development
- platform: python, self-hosted, cross-platform
- tags: academic-figures, ai-image-generation, scientific-illustration, paper-to-figure, fastapi, react, claude, gemini, prompt-generation, diagram-generation, web-server

## Member repositories
- LigphiDonk/academic-figure-generator (main) score 62

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:24.054875+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:47:37.013175+00:00, confidence not recorded.
  - readme: https://github.com/LigphiDonk/academic-figure-generator (fetched 2026-08-28T04:06:24.054875+00:00, sha d8d76e099ff4)
- Data as of 2026-08-30T08:39:29.467469+00:00.