# SagiPolaczek/NeuralSVG

Official implementation of NerualSVG

Repository: https://github.com/SagiPolaczek/NeuralSVG
Canonical: https://ross.abutalabs.com/products/neuralsvg
Homepage: https://sagipolaczek.github.io/NeuralSVG/
Language: Python
License: MIT
License Family: permissive
Last push: 2025-12-15T13:40:57+00:00

## Health v2 (maintenance only)
Score: 47/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 57, release rhythm 35, longevity 43
- inputs: {"age_days": 603, "days_push": 261, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1419, forks 32 (observed 2026-08-28T04:04:40.335039+00:00)

## What it is
Official PyTorch implementation of NeuralSVG, an ICCV 2025 paper that generates layered, editable SVG vector graphics from text prompts. It encodes a scene into a small MLP optimized with Score Distillation Sampling, supporting inference-time control like background color and aspect ratio.

## Use cases
- generate svg vector graphics from a text prompt
- text-to-vector image generation with layered shapes
- create editable svg illustrations from text
- control background color of generated svg
- generate svgs with different aspect ratios
- research code for score distillation sampling svg generation

## When to choose
- you need structured, layered, editable SVG output rather than raster images
- you want inference-time control (color palette, aspect ratio) from a single learned representation
- you are reproducing or building on the NeuralSVG research

## When to avoid
- you need fast, real-time generation - SDS optimization is slow
- you want a production text-to-image service with a polished UI
- you lack a GPU or don't want to run diffusion models locally

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, image-processing, graphics
- domain: machine-learning, computer-vision, graphics, artificial-intelligence
- platform: python, windows
- tags: text-to-vector, svg-generation, score-distillation, implicit-neural-representation, diffusion-models, research-code, iccv-2025, gpu, linux, macos

## Member repositories
- SagiPolaczek/NeuralSVG (main) score 47

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:40.335039+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 2026-08-30T04:37:51.593373+00:00, confidence not recorded.
  - readme: https://github.com/SagiPolaczek/NeuralSVG (fetched 2026-08-28T04:04:40.335039+00:00, sha de29f7c90729)
  - homepage: https://sagipolaczek.github.io/NeuralSVG/ (fetched 2026-08-29T11:50:15.025541+00:00, sha be85be766679)
- Data as of 2026-08-30T08:39:29.467469+00:00.