SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.02540 · ICLR · 2025

ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation

Xuefei Ning, Huazhong Yang, Yu Wang, Tianchen Zhao, Zinan Lin, Tongcheng Fang, Haofeng Huang, Rui Wan, Widyadewi Soedarmadji, Enshu Liu, Shiyao Li, Guohao Dai, and 3 more

arXiv · PDF · Open in the Atlas

Code that ran

3 of 10 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; 1 failure of our instrument; 7 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/2406.02540.json · badge: /api/ran/2406.02540.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
a-suozhang/vidit-q canonical (classifier label)
classifier basis: census
2 ran · 5 no recorded run
A-suozhang/ViDiT-Q reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 2 no recorded run
FunctionStatusWhere it lives
apply_func_to_submodules Ran
ran; our contract draft was wrong, not the code
a-suozhang/vidit-q/quant_utils/qdiff/utils.py
pointer only (licence: NONE) · get_code("be410f653fadfc80")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, a-suozhang/vidit-q 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.

extract_number_customize Ran
ran, honoured the contract we drafted
a-suozhang/vidit-q/eval/video/metrics/clip_score.py
pointer only (licence: NONE) · get_code("8dc23283b78375ff")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, a-suozhang/vidit-q 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.

open_image Ran
ran, honoured the contract we drafted
A-suozhang/ViDiT-Q/eval/image/evaluation/metrics/PickScore/trainer/scripts/eval_preference_predictor.py
pointer only (licence: NONE) · get_code("44b99c943200d432")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, A-suozhang/ViDiT-Q 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.

calc_probs_for_dataset Not yet run
unverified (harvested, no recorded run)
A-suozhang/ViDiT-Q/eval/image/evaluation/metrics/PickScore/trainer/scripts/eval_preference_predictor.py
pointer only (licence: NONE) · get_code("a530bdcaf456e5c8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, A-suozhang/ViDiT-Q 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.

calculate_activation_statistics Not yet run
unverified (harvested, no recorded run)
a-suozhang/vidit-q/eval/image/evaluation/fid_score.py
pointer only (licence: NONE) · get_code("40c33c72d49ca85f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, a-suozhang/vidit-q 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.

calculate_clip_score Not yet run
unverified (harvested, no recorded run)
a-suozhang/vidit-q/eval/video/metrics/clip_score.py
pointer only (licence: NONE) · get_code("2aed6e00d59aba70")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, a-suozhang/vidit-q 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.

calculate_clip_temp_score Not yet run
unverified (harvested, no recorded run)
a-suozhang/vidit-q/eval/video/metrics/clip_score.py
pointer only (licence: NONE) · get_code("7bff88199cee559a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, a-suozhang/vidit-q 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.

calculate_frechet_distance Not yet run
unverified (harvested, no recorded run)
a-suozhang/vidit-q/eval/image/evaluation/fid_score.py
pointer only (licence: NONE) · get_code("0def50a351111624")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, a-suozhang/vidit-q 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_activations Not yet run
unverified (harvested, no recorded run)
a-suozhang/vidit-q/eval/image/evaluation/fid_score.py
pointer only (licence: NONE) · get_code("7961d0b08426e139")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, a-suozhang/vidit-q 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.

infer_example Not yet run
unverified (harvested, no recorded run)
A-suozhang/ViDiT-Q/eval/image/evaluation/metrics/PickScore/trainer/scripts/eval_preference_predictor.py
pointer only (licence: NONE) · get_code("ee8210e9a8649299")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, A-suozhang/ViDiT-Q 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.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 1 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.

FunctionAlso present inEarliest-datedOthers named
calculate_frechet_distance 74 other papers
61 dated earlier, 3 the same month, 9 later, 1 same year, order not determinable
1610.09585 (2016-10)
Conditional Image Synthesis With Auxiliary Classifier GANs
1706.08500 (2017-06)
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
1807.11458 (2018-07)
To learn image super-resolution, use a GAN to learn how to do image degradation first
and 71 more not named here
calculate_clip_temp_score 1 other paper
1 dated earlier
2310.11440 (2023-10)
EvalCrafter: Benchmarking and Evaluating Large Video Generation Models

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

Diffusion transformers have demonstrated remarkable performance in visual generation tasks, such as generating realistic images or videos based on textual instructions. However, larger model sizes and multi-frame processing for video generation lead to increased computational and memory costs, posing challenges for practical deployment on edge devices. Post-Training Quantization (PTQ) is an effective method for reducing memory costs and computational complexity. When quantizing diffusion transformers, we find that existing quantization methods face challenges when applied to text-to-image and video tasks. To address these challenges, we begin by systematically analyzing the source of quantization error and conclude with the unique challenges posed by DiT quantization. Accordingly, we design an improved quantization scheme: ViDiT-Q (Video & Image Diffusion Transformer Quantization), tailored specifically for DiT models. We validate the effectiveness of ViDiT-Q across a variety of text-to-image and video models, achieving W8A8 and W4A8 with negligible degradation in visual quality and metrics. Additionally, we implement efficient GPU kernels to achieve practical 2-2.5x memory saving and a 1.4-1.7x end-to-end latency speedup.

For agents

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

get_harvested_code_for_paper("2406.02540")
get_code_for_paper("2406.02540")
have("2406.02540")

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

curl https://syntology.ai/api/ran/2406.02540.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.02540.svg)](https://syntology.ai/paper/2406.02540)

Connect an agent — have() is free.