Papers › SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow

SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow

17 Jul 2024arXiv:2407.12718archive 2025-07-28

Yuanzhi Zhu, Xingchao Liu, Qiang Liu

Diffusion models excel in high-quality generation but suffer from slow inference due to iterative sampling. While recent methods have successfully transformed diffusion models into one-step generators, they neglect model size reduction, limiting their applicability in compute-constrained scenarios. This paper aims to develop small, efficient one-step diffusion models based on the powerful rectified flow framework, by exploring joint compression of inference steps and model size. The rectified flow framework trains one-step generative models using two operations, reflow and distillation. Compared with the original framework, squeezing the model size brings two new challenges: (1) the initialization mismatch between large teachers and small students during reflow; (2) the underperformance of naive distillation on small student models. To overcome these issues, we propose Annealing Reflow and Flow-Guided Distillation, which together comprise our SlimFlow framework. With our novel framework, we train a one-step diffusion model with an FID of 5.02 and 15.7M parameters, outperforming the previous state-of-the-art one-step diffusion model (FID=6.47, 19.4M parameters) on CIFAR10. On ImageNet 64×64 and FFHQ 64×64, our method yields small one-step diffusion models that are comparable to larger models, showcasing the effectiveness of our method in creating compact, efficient one-step diffusion models.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 9 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 9 ran (4 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

yuanzhi-zhu/SlimFlow officialmentioned in papermentioned on GitHubpytorchSyntology: 9 samples, 9 ran (5 instrument-failed) · 0 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

9 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
2ran · our draft was wrong
3ran; the contract check could not run
3ran

Licence: 9 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from yuanzhi-zhu/SlimFlow. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

yuanzhi-zhu/SlimFlow official repository 9 samples, 9 ran (5 instrument-failed) · 0 unverified
get_act in 56 papers models/layers.py ran · our draft was wrong no licence file found · pointer only · db5f935a1d6b4c2c · report fixture: signature config:Config/0/? · returned ReLU · level recorded 2026-09-25
get_normalization in 25 papers models/normalization.py ran no licence file found · pointer only · 1b8adb3294e53c6d · report fixture: signature config:Config/0/?, conditional:bool/0/bool · returned type · level recorded 2026-09-25
get_weight in 21 papers models/up_or_down_sampling.py ran no licence file found · pointer only · 8db300b9f1afb2d3 · report fixture: signature module:callable/0/?, shape:tuple/1/int, weight_var:str/0/str, kernel_init:callable/0/? · returned Tensor · level recorded 2026-09-25
load_tmp_data generate_data.py ran · honoured contract no licence file found · pointer only · 9797498a8def79a5 · report fixture: signature data_root:str/0/str · returned tuple · level recorded 2026-09-24
naive_downsample_2d in 7 papers models/up_or_down_sampling.py ran; the contract check could not run (RAISES) no licence file found · pointer only · e0ca74cc0ccd0e50 · report fixture: signature x:Tensor/4/float, factor:int/0/int · returned Tensor · level recorded 2026-09-25
naive_upsample_2d in 7 papers models/up_or_down_sampling.py ran; the contract check could not run (RAISES) no licence file found · pointer only · f425357463a3de36 · report fixture: signature x:Tensor/4/float, factor:int/0/int · returned Tensor · level recorded 2026-09-25
ncsn_conv1x1 in 21 papers models/layers.py ran no licence file found · pointer only · 85b2235eb7afaa4f · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, bias:bool/0/bool, dilation:int/0/int, init_scale:float/0/float, padding:int/0/int · returned Conv2d · level recorded 2026-09-26
variance_scaling in 31 papers models/layers.py ran · our draft was wrong no licence file found · pointer only · 3ac11bfe0ae80195 · report fixture: signature scale:float/0/float, mode:str/0/str, distribution:str/0/str, in_axis:int/0/int, out_axis:int/0/int, dtype:dtype/0/?, device:str/0/str · returned function · level recorded 2026-09-24
weight_init in 73 papers models/edm_networks.py ran; the contract check could not run (RAISES) no licence file found · pointer only · d41a4250066bce93 · report fixture: signature shape:tuple/1/int, mode:str/0/str, fan_in:int/0/int, fan_out:int/0/int · returned Tensor · level recorded 2026-09-22

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections