SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.08403 · 2023

Instant3D: Instant Text-to-3D Generation

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 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; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 6 failures of our instrument; 3 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/2311.08403.json · badge: /api/ran/2311.08403.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
ming1993li/instant3dcodes canonical (classifier label)
classifier basis: census
8 ran · 3 no recorded run
FunctionStatusWhere it lives
FOV_to_intrinsics Ran
ran, honoured the contract we drafted
ming1993li/instant3dcodes/camera_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from hse1032/Adversarial-Generation-of-Hierarchical-Gaussians-for-3D-Generative-Model, is pointer only (licence: NONE) · get_code("eef98780cbfa6ee7")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from hse1032/Adversarial-Generation-of-Hierarchical-Gaussians-for-3D-Generative-Model, and GitHub detected no licence in that repository 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.

exists Ran
ran, violated the contract we drafted
ming1993li/instant3dcodes/training/generator_modules.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ThomasMrY/VCT, and GitHub detected no licence in that repository 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
ming1993li/instant3dcodes/dnnlib/util.py
pointer only (licence: MIT); 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: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ntuaislab/DRAG, and GitHub could not classify the licence of that repository (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.

format_time_brief Ran
ran; our contract draft was wrong, not the code
ming1993li/instant3dcodes/dnnlib/util.py
pointer only (licence: MIT); 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: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ntuaislab/DRAG, and GitHub could not classify the licence of that repository (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_text_embeddings_over_views Ran
ran; our contract draft was wrong, not the code
ming1993li/instant3dcodes/training/loss.py
code served (permissive licence) · get_code("3bb3aa07bd779705")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) 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

torch.manual_seed(0)

# Construct valid arguments for interpolate_text_embeddings_over_views
batch_size = 2
embedding_dim = 4

# all_embeddings: dict with keys 'front', 'side', 'back', each containing tensors of shape (batch_size, embedding_dim)
all_embeddings = {
    'front': torch.randn(batch_size, embedding_dim),
    'side': torch.randn(batch_size, embedding_dim),
    'back': torch.randn(batch_size, embedding_dim),
}

# all_azimuths: tensor of shape (batch_size,) with azimuth values
all_azimuths = torch.tensor([100.0, 200.0])

ARGS = {
    'all_embeddings': all_embeddings,
    'all_azimuths': all_azimuths,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 2, dtype family float, shape (2, 4) — shape (2, 4) 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
normalize_2nd_moment Ran
ran; our contract draft was wrong, not the code
ming1993li/instant3dcodes/training/generator_modules.py
pointer only (licence: MIT); the stored copy get_code serves, from POSTECH-CVLab/PyTorch-StudioGAN, is pointer only (licence: NOASSERTION) · get_code("670fe68b890c9792")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from POSTECH-CVLab/PyTorch-StudioGAN, and GitHub could not classify the licence of that repository (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
ming1993li/instant3dcodes/calc_metrics.py
pointer only (licence: MIT); 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: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from nv-tlabs/GET3D, and GitHub could not classify the licence of that repository (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.

safe_normalize Ran
ran; our contract draft was wrong, not the code
ming1993li/instant3dcodes/training/generator_modules.py
code served (permissive licence) · get_code("2a2e82bccee97963")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) 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

torch.manual_seed(0)

# The function safe_normalize takes a tensor x and an optional eps parameter
# It normalizes x along the last dimension by dividing by the L2 norm (clamped)
# x should be a tensor of any shape
# eps is a small float for numerical stability (default 1e-20)

x = torch.randn(2, 4)  # Small batch of 2, with 4-dimensional vectors
eps = 1e-20

ARGS = {
    "x": x,
    "eps": eps,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 2, dtype family float, shape (2, 4) — shape (2, 4) 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
ask_yes_no Not yet run
unverified (harvested, no recorded run)
ming1993li/instant3dcodes/dnnlib/util.py
code served (permissive licence) · get_code("9d31d2c4cd16bb2d")
How it ran

no invocation recorded.

compute_is Not yet run
unverified (harvested, no recorded run)
ming1993li/instant3dcodes/metrics/inception_score.py
pointer only (licence: MIT); the stored copy get_code serves, from hse1032/Adversarial-Generation-of-Hierarchical-Gaussians-for-3D-Generative-Model, is pointer only (licence: NONE) · get_code("fc49fa553c005268")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from hse1032/Adversarial-Generation-of-Hierarchical-Gaussians-for-3D-Generative-Model, and GitHub detected no licence in that repository 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.

reduce_tensor Not yet run
unverified (harvested, no recorded run)
ming1993li/instant3dcodes/training/loss.py
code served (permissive licence) · get_code("3efe35e36ec50fd3")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 9 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 7 the same month, 9 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.

FunctionAlso present inEarliest-datedOthers named
exists 486 other papers
247 dated earlier, 14 the same month, 219 later, 4 same year, order not determinable, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
format_time 73 other papers
20 dated earlier, 2 the same month, 50 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
20 dated earlier, 2 the same month, 46 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
17 dated earlier, 1 the same month, 49 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
parse_comma_separated_list 13 other papers
8 dated earlier, 1 the same month, 4 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
normalize_2nd_moment 7 other papers
4 dated earlier, 3 later
2107.04589 (2021-07)
ViTGAN: Training GANs with Vision Transformers
2206.09479 (2022-06)
StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesis
2305.12734 (2023-05)
EMEF: Ensemble Multi-Exposure Image Fusion
and 4 more not named here
compute_is 5 other papers
2 dated earlier, 1 the same month, 2 later
2202.00273 (2022-02)
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
2306.04675 (2023-06)
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
2311.17857 (2023-11)
Gaussian Shell Maps for Efficient 3D Human Generation
and 2 more not named here
FOV_to_intrinsics 4 other papers
1 dated earlier, 1 the same month, 2 later
2304.10263 (2023-04)
PREIM3D: 3D Consistent Precise Image Attribute Editing from a Single Image
2311.17857 (2023-11)
Gaussian Shell Maps for Efficient 3D Human Generation
2405.09879 (2024-05)
Generative Unlearning for Any Identity
and 1 more not named here
reduce_tensor 1 other paper
1 later
aaai_29654 (2024 (year only))
Cycle Self-Refinement for Multi-Source Domain Adaptation

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

Text-to-3D generation has attracted much attention from the computer vision community. Existing methods mainly optimize a neural field from scratch for each text prompt, relying on heavy and repetitive training cost which impedes their practical deployment. In this paper, we propose a novel framework for fast text-to-3D generation, dubbed Instant3D. Once trained, Instant3D is able to create a 3D object for an unseen text prompt in less than one second with a single run of a feedforward network. We achieve this remarkable speed by devising a new network that directly constructs a 3D triplane from a text prompt. The core innovation of our Instant3D lies in our exploration of strategies to effectively inject text conditions into the network. In particular, we propose to combine three key mechanisms: cross-attention, style injection, and token-to-plane transformation, which collectively ensure precise alignment of the output with the input text. Furthermore, we propose a simple yet effective activation function, the scaled-sigmoid, to replace the original sigmoid function, which speeds up the training convergence by more than ten times. Finally, to address the Janus (multi-head) problem in 3D generation, we propose an adaptive Perp-Neg algorithm that can dynamically adjust its concept negation scales according to the severity of the Janus problem during training, effectively reducing the multi-head effect. Extensive experiments on a wide variety of benchmark datasets demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods both qualitatively and quantitatively, while achieving significantly better efficiency. The code, data, and models are available at https://github.com/ming1993li/Instant3DCodes.

For agents

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

get_harvested_code_for_paper("2311.08403")
get_code_for_paper("2311.08403")
have("2311.08403")

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

curl https://syntology.ai/api/ran/2311.08403.json

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

[![Syntology run record](https://syntology.ai/api/ran/2311.08403.svg)](https://syntology.ai/paper/2311.08403)

Connect an agent — have() is free.