# ToTheBeginning/PuLID

[NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment

Repository: https://github.com/ToTheBeginning/PuLID
Canonical: https://ross.abutalabs.com/products/pulid
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2025-07-31T18:08:38+00:00

## Health v2 (maintenance only)
Score: 40/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 34, release rhythm 35, longevity 62
- inputs: {"age_days": 868, "days_push": 398, "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 3550, forks 268 (observed 2026-08-28T04:08:09.539582+00:00)

## What it is
PuLID is the official PyTorch implementation of a NeurIPS 2024 method for inserting a specific person's identity into text-to-image generation via contrastive alignment, supporting SDXL and FLUX models. It ships pretrained models, local Gradio demos, and HuggingFace/Replicate demos, running on consumer GPUs with as little as 12-16GB VRAM.

## Use cases
- generate images of a specific person from a reference photo
- preserve face identity in AI portrait generation
- customize FLUX or SDXL outputs with a consistent character
- create consistent avatars across multiple generated images
- run identity-preserving image generation on a consumer GPU
- reproduce PuLID research results

## When to choose
- you need high-fidelity face identity preservation in text-to-image generation
- you want a research-backed method with pretrained checkpoints for SDXL or FLUX
- you have a modest GPU (12-16GB) and want local inference
- you want to try the method quickly via HuggingFace or Replicate demos

## When to avoid
- you need multi-subject or try-on customization - consider the authors' DreamO framework instead
- you have no GPU available for local inference
- you need a production API service rather than a research codebase
- you work with non-face subject customization

## Facets
- artifact type: library
- maturity: active
- function: image-processing, machine-learning, stable-diffusion, deep-learning
- domain: artificial-intelligence, image-processing, computer-vision
- platform: python
- tags: face-customization, id-preservation, text-to-image, flux, gradio-demo, research-paper, gpu, linux

## Member repositories
- ToTheBeginning/PuLID (main) score 40

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:09.539582+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 2026-08-29T18:34:20.825737+00:00, confidence not recorded.
  - readme: https://github.com/ToTheBeginning/PuLID (fetched 2026-08-28T04:08:09.539582+00:00, sha 5454dc70e00e)
- Data as of 2026-08-30T08:39:29.467469+00:00.