SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.05239 · 2023

SwiftBrush: One-Step Text-to-Image Diffusion Model with Variational Score Distillation

arXiv · PDF · Open in the Atlas

Code that ran

5 of 8 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 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/2312.05239.json · badge: /api/ran/2312.05239.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
vinairesearch/swiftbrush canonical (classifier label)
classifier basis: census
5 ran · 3 no recorded run
FunctionStatusWhere it lives
encode_prompt Ran
ran; our contract draft was wrong, not the code
vinairesearch/swiftbrush/train_swiftbrush.py
pointer only (licence: NOASSERTION) · get_code("1d3562ea7817fc97")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vinairesearch/swiftbrush (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.

inference Ran
ran, honoured the contract we drafted
vinairesearch/swiftbrush/infer.py
pointer only (licence: NOASSERTION) · get_code("592a4f81e9ecdad6")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vinairesearch/swiftbrush (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.

predict_original Ran
ran; our contract draft was wrong, not the code
vinairesearch/swiftbrush/infer.py
pointer only (licence: NOASSERTION) · get_code("bbcbad7cfc48fa86")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vinairesearch/swiftbrush (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.

process_prompt_data Ran
ran; our contract draft was wrong, not the code
vinairesearch/swiftbrush/prepare.py
pointer only (licence: NOASSERTION) · get_code("ae1dcac9d4a46dc5")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vinairesearch/swiftbrush (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.

wrapper_process_prompt_data Ran
ran, honoured the contract we drafted
vinairesearch/swiftbrush/prepare.py
pointer only (licence: NOASSERTION) · get_code("7fa8f820462aa858")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vinairesearch/swiftbrush (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.

encode_prompt Not yet run
unverified (harvested, no recorded run)
vinairesearch/swiftbrush/infer.py
pointer only (licence: NOASSERTION) · get_code("24114a88cc0719ad")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vinairesearch/swiftbrush (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.

import_model_class_from_model_name_or_path Not yet run
unverified (harvested, no recorded run)
vinairesearch/swiftbrush/train_swiftbrush.py
pointer only (licence: NOASSERTION) · get_code("a9091b7ab048802c")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vinairesearch/swiftbrush (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.

parse_args Not yet run
unverified (harvested, no recorded run)
vinairesearch/swiftbrush/train_swiftbrush.py
pointer only (licence: NOASSERTION) · get_code("e8819641f3b2f9f9")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, vinairesearch/swiftbrush (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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 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 8 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

Despite their ability to generate high-resolution and diverse images from text prompts, text-to-image diffusion models often suffer from slow iterative sampling processes. Model distillation is one of the most effective directions to accelerate these models. However, previous distillation methods fail to retain the generation quality while requiring a significant amount of images for training, either from real data or synthetically generated by the teacher model. In response to this limitation, we present a novel image-free distillation scheme named $\textbf{SwiftBrush}$. Drawing inspiration from text-to-3D synthesis, in which a 3D neural radiance field that aligns with the input prompt can be obtained from a 2D text-to-image diffusion prior via a specialized loss without the use of any 3D data ground-truth, our approach re-purposes that same loss for distilling a pretrained multi-step text-to-image model to a student network that can generate high-fidelity images with just a single inference step. In spite of its simplicity, our model stands as one of the first one-step text-to-image generators that can produce images of comparable quality to Stable Diffusion without reliance on any training image data. Remarkably, SwiftBrush achieves an FID score of $\textbf{16.67}$ and a CLIP score of $\textbf{0.29}$ on the COCO-30K benchmark, achieving competitive results or even substantially surpassing existing state-of-the-art distillation techniques.

For agents

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

get_harvested_code_for_paper("2312.05239")
get_code_for_paper("2312.05239")
have("2312.05239")

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

curl https://syntology.ai/api/ran/2312.05239.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.05239.svg)](https://syntology.ai/paper/2312.05239)

Connect an agent — have() is free.