Papers › Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in...

Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models

11 Apr 2024arXiv:2404.07724archive 2025-07-28

Tuomas Kynkäänniemi, Miika Aittala, Tero Karras, Samuli Laine, Timo Aila, Jaakko Lehtinen

Guidance is a crucial technique for extracting the best performance out of image-generating diffusion models. Traditionally, a constant guidance weight has been applied throughout the sampling chain of an image. We show that guidance is clearly harmful toward the beginning of the chain (high noise levels), largely unnecessary toward the end (low noise levels), and only beneficial in the middle. We thus restrict it to a specific range of noise levels, improving both the inference speed and result quality. This limited guidance interval improves the record FID in ImageNet-512 significantly, from 1.81 to 1.40. We show that it is quantitatively and qualitatively beneficial across different sampler parameters, network architectures, and datasets, including the large-scale setting of Stable Diffusion XL. We thus suggest exposing the guidance interval as a hyperparameter in all diffusion models that use guidance.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2404.07724")

Code

Syntology Ran 5 of 7 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 3 ran with no contract checked.

By repository: official repository: 7 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

kynkaat/guidance-interval officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
vectorspacelab/omnigen2 mentioned on GitHubpytorchApache-2.0 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

7 samples harvested; 5 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · our draft was wrong
3ran
2unverified

Licence: 0 of the 7 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 kynkaat/guidance-interval. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

compute_fid kynkaat/guidance-interval/metrics/frechet_inception_distance.py official repository ran Apache-2.0 (permissive) · 4f8bb5961682a237 · report
count_images_in_zip kynkaat/guidance-interval/utils.py official repository ran Apache-2.0 (permissive) · 7778f5836023c242 · report
decode_latents kynkaat/guidance-interval/sampling/sample_images.py official repository ran Apache-2.0 (permissive) · 20795df1064e5659 · report
format_time kynkaat/guidance-interval/dnnlib/util.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 674eca7b9e1b6439 · report
format_time_brief kynkaat/guidance-interval/dnnlib/util.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 32af001972a0699f · report
ask_yes_no kynkaat/guidance-interval/dnnlib/util.py official repository unverified Apache-2.0 (permissive) · 9d31d2c4cd16bb2d · report
edm_sampler kynkaat/guidance-interval/sampling/edm_sampler.py official repository unverified Apache-2.0 (permissive) · a1b475ef1c3f3263 · report

Tasks

Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation ImageNet 512x512 EDM2-XXL w/ guidance interval FID 1.40 #9 of 52 Archive leaderboard report
Image Generation ImageNet 512x512 EDM2-S w/ guidance interval FID 1.68 #14 of 52 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

DiffusionSPEED

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