SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2102.02766 · 2021

Designing an Encoder for StyleGAN Image Manipulation

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2102.02766.json · badge: /api/ran/2102.02766.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
omertov/encoder4editing canonical (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
FunctionStatusWhere it lives
get_latents Ran
ran; our contract draft was wrong, not the code
omertov/encoder4editing/scripts/inference.py
code served (permissive licence) · get_code("d027eaaf8c4b5c3e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, ndim 3, dtype family float, shape (2, 18, 512) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

class StandInEncoder(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(3, 12)
    
    def forward(self, x):
        # Returns codes of shape (batch, 18, 512) for the general case
        batch_size = x.shape[0]
        return torch.randn(batch_size, 18, 512)

class StandInOpts:
    def __init__(self):
        self.start_from_latent_avg = True

class StandInNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.encoder = StandInEncoder()
        self.opts = StandInOpts()
        self.latent_avg = torch.randn(1, 18, 512)

net = StandInNet()
x = torch.randn(2, 3, 64, 64)
is_cars = False

ARGS = {
    'net': net,
    'x': x,
    'is_cars': is_cars
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (2, 18, 512) — shape (2, 18, 512) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_all_latents Not yet run
unverified (harvested, no recorded run)
omertov/encoder4editing/scripts/inference.py
code served (permissive licence) · get_code("56b7de72d9413f8f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recently, there has been a surge of diverse methods for performing image editing by employing pre-trained unconditional generators. Applying these methods on real images, however, remains a challenge, as it necessarily requires the inversion of the images into their latent space. To successfully invert a real image, one needs to find a latent code that reconstructs the input image accurately, and more importantly, allows for its meaningful manipulation. In this paper, we carefully study the latent space of StyleGAN, the state-of-the-art unconditional generator. We identify and analyze the existence of a distortion-editability tradeoff and a distortion-perception tradeoff within the StyleGAN latent space. We then suggest two principles for designing encoders in a manner that allows one to control the proximity of the inversions to regions that StyleGAN was originally trained on. We present an encoder based on our two principles that is specifically designed for facilitating editing on real images by balancing these tradeoffs. By evaluating its performance qualitatively and quantitatively on numerous challenging domains, including cars and horses, we show that our inversion method, followed by common editing techniques, achieves superior real-image editing quality, with only a small reconstruction accuracy drop.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2102.02766")
get_code_for_paper("2102.02766")
have("2102.02766")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2102.02766.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2102.02766.svg)](https://syntology.ai/paper/2102.02766)

Connect an agent — have() is free.