# iPERDance/iPERCore

Liquid Warping GAN with Attention: A Unified Framework for Human Image Synthesis

Repository: https://github.com/iPERDance/iPERCore
Canonical: https://ross.abutalabs.com/products/ipercore
Homepage: https://iperdance.github.io/work/impersonator-plus-plus.html
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2023-05-12T03:23:38+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": 2115, "days_push": 1209, "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 2393, forks 304 (observed 2026-08-28T04:06:43.426903+00:00)

## What it is
Impersonator++ (iPERCore) is a PyTorch implementation of Liquid Warping GAN with Attention, a unified framework for human image synthesis. It supports human motion imitation, appearance transfer, and novel view synthesis from a single source image, producing high-resolution outputs up to 1024x1024.

## Use cases
- animate a person in a photo to imitate a motion video
- transfer clothing or appearance between people in images
- synthesize novel views of a person from a single image
- create bullet-time effect videos from a still photo
- generate multi-view outputs of a human pose
- research on GAN-based human pose transfer

## When to choose
- you need motion imitation or appearance transfer from a single reference image
- you want high-resolution (512/1024) human synthesis results
- you need a unified model handling multiple human synthesis tasks
- you are doing research on pose transfer or liquid warping GANs

## When to avoid
- you need a production-ready, actively maintained product
- you lack a CUDA GPU, since inference is compute-heavy
- you need real-time video generation
- you want a simple app rather than a Python research codebase

## Facets
- artifact type: library
- maturity: maintenance
- function: image-processing, machine-learning, deep-learning, computer-vision
- domain: computer-vision, image-processing, deep-learning, machine-learning
- platform: python, windows
- tags: gan, human-image-synthesis, motion-imitation, appearance-transfer, novel-view-synthesis, pose-transfer, research, linux, gpu

## Member repositories
- iPERDance/iPERCore (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:43.426903+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 2026-08-30T02:34:25.331765+00:00, confidence not recorded.
  - readme: https://github.com/iPERDance/iPERCore (fetched 2026-08-28T04:06:43.426903+00:00, sha eb22a76d901b)
  - homepage: https://iperdance.github.io/work/impersonator-plus-plus.html (fetched 2026-08-29T10:14:58.199384+00:00, sha 09111ee3caf5)
- Data as of 2026-08-30T08:39:29.467469+00:00.