#4343rd of 75 in Image and videoFor image, video and design, image and design, science, health and research, research and papers
autofigure-edit
Turns paper method text into editable SVG figures with a browser editor
Live demo ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 4.4k
- License
- MIT
- Last commit
- Jul 2026
- Last release
- Apr 2026
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
AutoFigure-Edit generates a raster draft figure from method-section text with an image model. It then segments icons with SAM3, removes backgrounds with RMBG-2.0, and has an LLM write a placeholder SVG that is filled with the cropped icons. The result opens in an embedded SVG-Edit canvas, and an existing stage-1 figure can be imported to skip generation.
Who it is for: Researchers who need editable method-overview figures for papers
Strengths
- Outputs editable SVG with separate text, shapes and icon crops, not a flat raster
- SAM3 can run through Roboflow or fal.ai, so no local GPU install is needed
- Supports OpenRouter, Gemini, OpenAI Responses and any OpenAI-compatible /v1 endpoint
- Accepts a reference image for style transfer and an existing figure to skip step 1
Weaknesses
- Requires paid LLM API keys plus a Hugging Face token with access to RMBG-2.0
- Local SAM3 is not vendored and targets Python 3.12+, PyTorch 2.7+, CUDA 12.6
- Icons are cropped raster images, so only layout and text are fully vector
- Quality depends on the chosen image and SVG models; no offline model path is documented
What it needs
- GPU optional
- Docker + Compose
- Needs Hugging Face token (briaai/RMBG-2.0), LLM provider API key (OpenRouter, Gemini, OpenAI, Bianxie or custom), SAM3 locally, or Roboflow / fal.ai API, Docker Compose (optional)
- Models: OpenRouter, Google Gemini, OpenAI Responses (gpt-5.5, gpt-image-2), OpenAI-compatible custom endpoints, SAM3
- port 8000
Also in Image and video
See all 75| Rank | Project | Score |
|---|---|---|
| 1 | frigateLocal NVR with realtime object detection for IP cameras | 93 out of 100 |
| 2 | MoneyPrinterTurboGenerates short videos from a topic, with script, footage, voiceover and subtitles | 88 out of 100 |
| 3 | toonflow-appInfinite-canvas tool for AI short drama and comic video production | 87 out of 100 |
| #4 | InvokeAIWeb UI for diffusion image generation with inpainting canvas and node workflows | 86 out of 100 |
| #5 | ComfyUINode-graph editor for running diffusion image, video, audio and 3D workflows | 85 out of 100 |