SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.14176 · 2024

SwiftBrush v2: Make Your One-step Diffusion Model Better Than Its Teacher

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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, 0 violated it and 0 have no contract verdict; 0 failures of our instrument; 0 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/2408.14176.json · badge: /api/ran/2408.14176.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/swiftbrushv2 canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
tokenize_captions Ran
ran, honoured the contract we drafted
vinairesearch/swiftbrushv2/infer_by_prompt.py
code served (permissive licence) · get_code("b979e8faa64c0d12")
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 int, shape (3, 77) 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 random
import numpy as np
from unittest.mock import Mock

# Create a minimal tokenizer stand-in that has the required interface
class MinimalTokenizer:
    def __init__(self):
        self.model_max_length = 77
    
    def __call__(self, captions, max_length, padding, truncation, return_tensors):
        # Return a mock object with input_ids attribute
        import torch
        torch.manual_seed(0)
        # Create dummy token ids for each caption
        batch_size = len(captions)
        token_ids = torch.randint(0, 1000, (batch_size, max_length), dtype=torch.long)
        
        result = Mock()
        result.input_ids = token_ids
        return result

# Prepare test data for examples parameter
examples = [
    "a photo of a cat",  # plain string
    ["a dog", "a running dog", "a dog in the park"],  # list of strings
    np.array(["a bird", "a flying bird"]),  # numpy array of strings
]

# Create tokenizer instance
tokenizer = MinimalTokenizer()

# Set random seed for reproducibility
random.seed(0)

# Construct ARGS dict with all parameters
ARGS = {
    "examples": examples,
    "tokenizer": tokenizer,
    "is_train": True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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 int, shape (3, 77) — shape (3, 77) 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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 1 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

In this paper, we aim to enhance the performance of SwiftBrush, a prominent one-step text-to-image diffusion model, to be competitive with its multi-step Stable Diffusion counterpart. Initially, we explore the quality-diversity trade-off between SwiftBrush and SD Turbo: the former excels in image diversity, while the latter excels in image quality. This observation motivates our proposed modifications in the training methodology, including better weight initialization and efficient LoRA training. Moreover, our introduction of a novel clamped CLIP loss enhances image-text alignment and results in improved image quality. Remarkably, by combining the weights of models trained with efficient LoRA and full training, we achieve a new state-of-the-art one-step diffusion model, achieving an FID of 8.14 and surpassing all GAN-based and multi-step Stable Diffusion models. The project page is available at https://swiftbrushv2.github.io.

For agents

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

get_harvested_code_for_paper("2408.14176")
get_code_for_paper("2408.14176")
have("2408.14176")

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

curl https://syntology.ai/api/ran/2408.14176.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.14176.svg)](https://syntology.ai/paper/2408.14176)

Connect an agent — have() is free.