RishabSA/Sketch2Graphviz
Sketch2Graphviz allows you to convert sketches or images of graphs and flowcharts to proper Graphviz code using a LoRA fine-tuned Llama 3.2 11B Vision and Retrieval-Augmented Generation (RAG) through a vector database built with PostgreSQL and PGVector, making a previously tedious, manual task fast and effortless.
This tool helps diagram creators and documentation specialists quickly convert their hand-drawn sketches or image-based flowcharts and graphs into structured Graphviz DOT code. Simply upload an image or sketch a diagram directly on the interactive canvas, and the system generates the corresponding code. The output is editable DOT code and a live rendered SVG, useful for anyone needing to standardize or digitalize their diagrams efficiently.
Use this if you frequently create diagrams and want to automate the tedious process of converting visual sketches into machine-readable Graphviz DOT code.
Not ideal if you primarily create diagrams directly within code or existing diagramming software rather than sketching them out first.
Stars
7
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 28, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/RishabSA/Sketch2Graphviz"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
filipstrand/mflux
MLX native implementations of state-of-the-art generative image models
potamides/DeTikZify
Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ.
FoundationVision/Infinity
[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis
zai-org/CogView
Text-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image...
EleutherAI/DALLE-mtf
Open-AI's DALL-E for large scale training in mesh-tensorflow.