SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.09867 · NeurIPS · 2024

Towards Kinetic Manipulation of the Latent Space

Diego Porres

arXiv · PDF · Open in the Atlas

Code that ran

16 of 18 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; 4 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 12 failures of our instrument; 2 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2409.09867.json · badge: /api/ran/2409.09867.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
PDillis/stylegan3-fun canonical (classifier label)
classifier basis: plan_row
16 ran · 2 no recorded run
FunctionStatusWhere it lives
parse_tuple Ran
ran, honoured the contract we drafted
PDillis/stylegan3-fun/dataset_tool.py
pointer only (licence: NONE); the stored copy get_code serves, from pdillis/stylegan3-fun, is pointer only (licence: NOASSERTION) · get_code("9cd07419f7c926f8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PDillis/stylegan3-fun when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

construct_heatmap Ran
ran; our contract draft was wrong, not the code
PDillis/stylegan3-fun/avg_spectra.py
pointer only (licence: NOASSERTION) · get_code("260d293a46551cc2")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, PDillis/stylegan3-fun (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

extract_layer_features Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
PDillis/stylegan3-fun/network_features.py
pointer only (licence: NOASSERTION) · get_code("15d4450343d8abcf")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, PDillis/stylegan3-fun (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

file_ext Ran
ran; our contract draft was wrong, not the code
PDillis/stylegan3-fun/dataset_tool.py
pointer only (licence: NONE); the stored copy get_code serves, from pdillis/stylegan3-fun, is pointer only (licence: NOASSERTION) · get_code("a2b45afa097b55b6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PDillis/stylegan3-fun when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

format_time Ran
ran; our contract draft was wrong, not the code
PDillis/stylegan3-fun/dnnlib/util.py
pointer only (licence: NONE); the stored copy get_code serves, from ntuaislab/DRAG, is pointer only (licence: NOASSERTION) · get_code("053fc534bc6bb989")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PDillis/stylegan3-fun when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

format_time_brief Ran
ran; our contract draft was wrong, not the code
PDillis/stylegan3-fun/dnnlib/util.py
pointer only (licence: NONE); the stored copy get_code serves, from ntuaislab/DRAG, is pointer only (licence: NOASSERTION) · get_code("77f4aa0649e7f404")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PDillis/stylegan3-fun when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_3d_perlin Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
PDillis/stylegan3-fun/fractalperlin.py
pointer only (licence: NOASSERTION) · get_code("6aae8094e6350fd5")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, PDillis/stylegan3-fun (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_available_layers Ran
ran; our contract draft was wrong, not the code
PDillis/stylegan3-fun/discriminator_synthesis.py
pointer only (licence: NOASSERTION) · get_code("579f771f8a222a25")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, PDillis/stylegan3-fun (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

interpolate_multiple_models Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
PDillis/stylegan3-fun/frankenstein_network.py
pointer only (licence: NOASSERTION) · get_code("01821f2dd2451cdf")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, PDillis/stylegan3-fun (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

layout_grid Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
PDillis/stylegan3-fun/gen_video.py
pointer only (licence: NONE) · get_code("456c172851946697")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PDillis/stylegan3-fun when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

make_transform Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
PDillis/stylegan3-fun/gen_images.py
pointer only (licence: NONE) · get_code("f47dff4b7b27bba7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PDillis/stylegan3-fun when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

maybe_min Ran
ran, honoured the contract we drafted
PDillis/stylegan3-fun/dataset_tool.py
pointer only (licence: NONE); the stored copy get_code serves, from pdillis/stylegan3-fun, is pointer only (licence: NOASSERTION) · get_code("dd1dc700e87f36cc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PDillis/stylegan3-fun when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

normalize_features Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
PDillis/stylegan3-fun/network_features.py
pointer only (licence: NOASSERTION) · get_code("50b389807d1aa840")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, PDillis/stylegan3-fun (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

parse_comma_separated_list Ran
ran; our contract draft was wrong, not the code
PDillis/stylegan3-fun/calc_metrics.py
pointer only (licence: NONE); the stored copy get_code serves, from nv-tlabs/GET3D, is pointer only (licence: NOASSERTION) · get_code("d01b68a634f71551")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PDillis/stylegan3-fun when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

parse_range Ran
ran, honoured the contract we drafted
PDillis/stylegan3-fun/gen_images.py
pointer only (licence: NONE) · get_code("236de8614a178382")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PDillis/stylegan3-fun when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

parse_vec2 Ran
ran, honoured the contract we drafted
PDillis/stylegan3-fun/gen_images.py
pointer only (licence: NONE) · get_code("180016b9227381b1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PDillis/stylegan3-fun when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ask_yes_no Not yet run
unverified (harvested, no recorded run)
PDillis/stylegan3-fun/dnnlib/util.py
pointer only (licence: NONE) · get_code("9d31d2c4cd16bb2d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PDillis/stylegan3-fun when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_2d_perlin Not yet run
unverified (harvested, no recorded run)
PDillis/stylegan3-fun/fractalperlin.py
pointer only (licence: NOASSERTION) · get_code("c68a128b986f1aac")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, PDillis/stylegan3-fun (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 12 are also present in other papers whose code we hold (12 with at least one paper dated earlier, 3 the same month, 11 later) and 6 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.

FunctionAlso present inEarliest-datedOthers named
format_time 73 other papers
45 dated earlier, 1 the same month, 26 later, 1 undated
2004.00049 (2020-04)
In-Domain GAN Inversion for Real Image Editing
2004.11660 (2020-04)
Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
2108.00946 (2021-08)
StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
and 70 more not named here
ask_yes_no 69 other papers
45 dated earlier, 1 the same month, 22 later, 1 undated
2004.00049 (2020-04)
In-Domain GAN Inversion for Real Image Editing
2004.11660 (2020-04)
Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
2108.00946 (2021-08)
StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
and 66 more not named here
format_time_brief 68 other papers
40 dated earlier, 1 the same month, 26 later, 1 undated
2108.00946 (2021-08)
StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
2202.00273 (2022-02)
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
2206.07695 (2022-06)
VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids
and 65 more not named here
file_ext 35 other papers
24 dated earlier, 11 later
2106.07023 (2021-06)
Styleformer: Transformer based Generative Adversarial Networks with Style Vector
2111.02175 (2021-11)
Discriminator Synthesis: On reusing the other half of Generative Adversarial Networks
2111.13792 (2021-11)
LAFITE: Towards Language-Free Training for Text-to-Image Generation
and 32 more not named here
maybe_min 35 other papers
24 dated earlier, 11 later
2106.07023 (2021-06)
Styleformer: Transformer based Generative Adversarial Networks with Style Vector
2111.02175 (2021-11)
Discriminator Synthesis: On reusing the other half of Generative Adversarial Networks
2111.13792 (2021-11)
LAFITE: Towards Language-Free Training for Text-to-Image Generation
and 32 more not named here
parse_comma_separated_list 13 other papers
12 dated earlier, 1 later
2112.07945 (2021-12)
Efficient Geometry-aware 3D Generative Adversarial Networks
2202.00273 (2022-02)
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
2206.07695 (2022-06)
VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids
and 10 more not named here
parse_vec2 11 other papers
9 dated earlier, 2 later
2106.12423 (2021-06)
Alias-Free Generative Adversarial Networks
2112.07945 (2021-12)
Efficient Geometry-aware 3D Generative Adversarial Networks
2202.00273 (2022-02)
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
and 8 more not named here
parse_range 9 other papers
6 dated earlier, 3 later
2106.12423 (2021-06)
Alias-Free Generative Adversarial Networks
2202.00273 (2022-02)
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
2206.07695 (2022-06)
VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids
and 6 more not named here
make_transform 8 other papers
6 dated earlier, 2 later
2106.12423 (2021-06)
Alias-Free Generative Adversarial Networks
2112.07945 (2021-12)
Efficient Geometry-aware 3D Generative Adversarial Networks
2202.00273 (2022-02)
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
and 5 more not named here
parse_tuple 7 other papers
5 dated earlier, 2 later
2111.02175 (2021-11)
Discriminator Synthesis: On reusing the other half of Generative Adversarial Networks
2202.00273 (2022-02)
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
2206.07695 (2022-06)
VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids
and 4 more not named here
layout_grid 6 other papers
5 dated earlier, 1 later
2202.00273 (2022-02)
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
2211.11208 (2022-11)
Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars
2303.13071 (2023-03)
PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360$^{\circ}$
and 3 more not named here
construct_heatmap 1 other paper
1 dated earlier
2206.00048 (2022-06)
PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANs

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

The latent space of many generative models are rich in unexplored valleys and mountains. The majority of tools used for exploring them are so far limited to Graphical User Interfaces (GUIs). While specialized hardware can be used for this task, we show that a simple feature extraction of pre-trained Convolutional Neural Networks (CNNs) from a live RGB camera feed does a very good job at manipulating the latent space with simple changes in the scene, with vast room for improvement. We name this new paradigm Visual-reactive Interpolation, and the full code can be found at https://github.com/PDillis/stylegan3-fun. Interaction with generative models such as Generative Adversarial Networks (GANs) [GPAM + 14] and diffusion-based text-to-image models (T2I) [SWMG15] has been relinquished to the land of software, specifically Graphical User Interfaces (GUIs). The main advantage of using these is the speed at which they can be modified and shared between users, in addition to simplifying interaction with the model, including it's high-dimensional latent space. However, we believe this also introduces a rift between the generative models and their users, if not also with their creators, as we forego the most basic interface: the human body. Since our aim is to control the image synthesis generation during a live performance show, we will quickly explore other already existing alternatives. Concretely, we will focus our attention to manipulate the latent space of StyleGAN1/2/2-ADA [KLA18, KLA + 19, KAH + 20], some of the most popular and widely trained networks, but we will look at inspiration for what has been done 38th Conference on Neural Information Processing Systems (NeurIPS 2024) Creative AI Track.

For agents

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

get_harvested_code_for_paper("2409.09867")
get_code_for_paper("2409.09867")
have("2409.09867")

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

curl https://syntology.ai/api/ran/2409.09867.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.09867.svg)](https://syntology.ai/paper/2409.09867)

Connect an agent — have() is free.