Papers › Long and Short Guidance in Score identity Distillation for One-Step Text-to-Image Generation

Long and Short Guidance in Score identity Distillation for One-Step Text-to-Image Generation

3 Jun 2024arXiv:2406.01561archive 2025-07-28

Mingyuan Zhou, Zhendong Wang, Huangjie Zheng, Hai Huang

Diffusion-based text-to-image generation models trained on extensive text-image pairs have shown the capacity to generate photorealistic images consistent with textual descriptions. However, a significant limitation of these models is their slow sample generation, which requires iterative refinement through the same network. In this paper, we enhance Score identity Distillation (SiD) by developing long and short classifier-free guidance (LSG) to efficiently distill pretrained Stable Diffusion models without using real training data. SiD aims to optimize a model-based explicit score matching loss, utilizing a score-identity-based approximation alongside the proposed LSG for practical computation. By training exclusively with fake images synthesized with its one-step generator, SiD equipped with LSG rapidly improves FID and CLIP scores, achieving state-of-the-art FID performance while maintaining a competitive CLIP score. Specifically, its data-free distillation of Stable Diffusion 1.5 achieves a record low FID of 8.15 on the COCO-2014 validation set, with a CLIP score of 0.304 at an LSG scale of 1.5, and an FID of 9.56 with a CLIP score of 0.313 at an LSG scale of 2. Our code and distilled one-step text-to-image generators are available at https://github.com/mingyuanzhou/SiD-LSG.

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="2406.01561")

Code

Syntology Ran 18 of 24 code samples harvested from 2 repositories linked to this paper; 6 have no recorded run. Of those that ran: 3 ran · honoured contract; 4 ran · our draft was wrong; 2 ran · fixture could not drive it; 9 ran with no contract checked.

By repository: official repository: 22 samples from 1 repository, 16 ran; community: 2 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

mingyuanzhou/sid-lsg officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
mingyuanzhou/sid 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

24 samples harvested; 18 ran; 3 honoured the contract we drafted; 6 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.

3ran · honoured contract
4ran · our draft was wrong
2ran · fixture could not drive it
9ran
6unverified

Licence: 2 of the 24 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

parse_tuple mingyuanzhou/SiD-LSG/cocodataset_tool.py official repository ran · honoured contract Apache-2.0 (permissive) · 9cd07419f7c926f8 · report
compute_distances mingyuanzhou/SiD-LSG/metrics/sid_precision_recall.py official repository ran Apache-2.0 (permissive) · 790b320b90341326 · report
encode_prompt mingyuanzhou/SiD-LSG/training/sid_sd_util.py official repository ran Apache-2.0 (permissive) · b4e975940805a660 · report
file_ext mingyuanzhou/SiD-LSG/cocodataset_tool.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · a2b45afa097b55b6 · report
find_latest_checkpoint mingyuanzhou/sid-lsg/sid_train.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 0021e29612552771 · report
format_time mingyuanzhou/SiD-LSG/dnnlib/util.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 674eca7b9e1b6439 · report
format_time_brief mingyuanzhou/SiD-LSG/dnnlib/util.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 32af001972a0699f · report
is_valid_metric mingyuanzhou/SiD-LSG/metrics/sid_metric_main.py official repository ran Apache-2.0 (permissive) · 147acc22e758c8e5 · report
maybe_min mingyuanzhou/SiD-LSG/cocodataset_tool.py official repository ran · honoured contract Apache-2.0 (permissive) · dd1dc700e87f36cc · report
parse_int_list mingyuanzhou/SiD-LSG/sid_metrics.py official repository ran · honoured contract Apache-2.0 (permissive) · cacd4f6ec202d9b4 · report
parse_tuple mingyuanzhou/SiD-LSG/dataset_tool.py official repository ran Apache-2.0 (permissive) · 07b21b35ecb4815c · report
register_metric mingyuanzhou/SiD-LSG/metrics/sid_metric_main.py official repository ran Apache-2.0 (permissive) · e574c21e7f007b61 · report
safe_load mingyuanzhou/SiD-LSG/metrics/sid_metric_utils.py official repository ran Apache-2.0 (permissive) · 2ff552e801a5c835 · report
setup_snapshot_image_grid mingyuanzhou/SiD-LSG/training/sid_training_loop.py official repository ran Apache-2.0 (permissive) · 4eb9bd36235b00bf · report
split_list mingyuanzhou/SiD-LSG/training/sid_training_loop.py official repository ran fingerprinted Apache-2.0 (permissive) · baad057101faa00e · report
tokenize_captions mingyuanzhou/SiD-LSG/training/sid_sd_util.py official repository ran Apache-2.0 (permissive) · a7ee9e9cfc473967 · report
ask_yes_no mingyuanzhou/SiD-LSG/dnnlib/util.py official repository unverified Apache-2.0 (permissive) · 9d31d2c4cd16bb2d · report
compute_fid_and_clip mingyuanzhou/SiD-LSG/metrics/sid_fid_and_clip.py official repository unverified Apache-2.0 (permissive) · 4df77172213d4bd0 · report
compute_pr mingyuanzhou/SiD-LSG/metrics/sid_precision_recall.py official repository unverified Apache-2.0 (permissive) · e687131b851cf012 · report
get_feature_detector_name mingyuanzhou/SiD-LSG/metrics/sid_metric_utils.py official repository unverified Apache-2.0 (permissive) · c127dc46d6966547 · report
sid_sd_sampler mingyuanzhou/sid-lsg/training/sid_sd_util.py official repository unverified Apache-2.0 (permissive) · 8c9557ae76612b77 · report
upcast_vae mingyuanzhou/sid-lsg/training/sid_sd_util.py official repository unverified Apache-2.0 (permissive) · abdafc09a34957ba · report
compute_clip_score mingukkang/gigagan/evaluation/evaluation.py community ran · fixture could not drive it no licence file found · pointer only · a3aaa665cb2c6e2a · report
tensor2pil mingukkang/gigagan/evaluation/evaluation.py community ran · fixture could not drive it no licence file found · pointer only · 11687d1d3ed1d3db · report

Tasks

Image GenerationText to Image GenerationText-to-Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-to-Image Generation COCO (Common Objects in Context) SiD-LSG (Data-free distillation, zero-shot FID) FID 8.15 #21 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) SiD-LSG (Data-free distillation, zero-shot FID) Zero shot FID 8.15 #21 of 69 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

CLIPDiffusion

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