# minivision-ai/photo2cartoon

人像卡通化探索项目 (photo-to-cartoon translation project)

Repository: https://github.com/minivision-ai/photo2cartoon
Canonical: https://ross.abutalabs.com/products/photo2cartoon
Language: Python
License: MIT
License Family: permissive
Topics: cartoon, deep-learning, computer-vision, gan, avatar-generator
Last push: 2022-06-12T08:57:21+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2329, "days_push": 1543, "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 4029, forks 769 (observed 2026-08-28T04:08:32.726529+00:00)

## What it is
A Python deep-learning project from Minivision that converts real portrait photos into cartoon-style avatars using unpaired image translation (a U-GAT-IT-based GAN with Soft-AdaLIN and a Face ID loss). It ships pretrained PyTorch and ONNX models, face detection/alignment, and portrait segmentation utilities.

## Use cases
- turn a portrait photo into a cartoon avatar
- generate cartoon-style profile pictures from selfies
- run photo-to-cartoon image translation with pretrained models
- train a GAN for unpaired photo-to-cartoon translation
- convert photos to cartoon style via onnx inference

## When to choose
- you want a ready pretrained model for stylizing human portraits into a realistic-leaning cartoon style
- you need a research reference for unpaired image translation with identity-preserving losses
- you want ONNX inference without a full PyTorch setup

## When to avoid
- you need general scene or object cartoonization - it is trained only on aligned human face portraits (originally young Asian women)
- you need a maintained production library - the project has not been updated since 2022 and depends on old PyTorch/TensorFlow versions
- you need paired pix2pix-style translation or non-portrait image-to-image tasks

## Facets
- artifact type: library
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing, deep-learning, artificial-intelligence
- platform: python
- tags: gan, avatar-generator, cartoonization, image-translation, ugatit, face-id-loss, onnx, portrait, gpu

## Member repositories
- minivision-ai/photo2cartoon (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:32.726529+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 2026-08-29T18:23:51.515237+00:00, confidence not recorded.
  - readme: https://github.com/minivision-ai/photo2cartoon (fetched 2026-08-28T04:08:32.726529+00:00, sha 45829fa70370)
- Data as of 2026-08-30T08:39:29.467469+00:00.