Papers › Curriculum Direct Preference Optimization for Diffusion and Consistency Models

Curriculum Direct Preference Optimization for Diffusion and Consistency Models

22 May 2024CVPR 2025 1arXiv:2405.13637archive 2025-07-28

Florinel-Alin Croitoru, Vlad Hondru, Radu Tudor Ionescu, Nicu Sebe, Mubarak Shah

Direct Preference Optimization (DPO) has been proposed as an effective and efficient alternative to reinforcement learning from human feedback (RLHF). In this paper, we propose a novel and enhanced version of DPO based on curriculum learning for text-to-image generation. Our method is divided into two training stages. First, a ranking of the examples generated for each prompt is obtained by employing a reward model. Then, increasingly difficult pairs of examples are sampled and provided to a text-to-image generative (diffusion or consistency) model. Generated samples that are far apart in the ranking are considered to form easy pairs, while those that are close in the ranking form hard pairs. In other words, we use the rank difference between samples as a measure of difficulty. The sampled pairs are split into batches according to their difficulty levels, which are gradually used to train the generative model. Our approach, Curriculum DPO, is compared against state-of-the-art fine-tuning approaches on nine benchmarks, outperforming the competing methods in terms of text alignment, aesthetics and human preference. Our code is available at https://github.com/CroitoruAlin/Curriculum-DPO.

PaperPDFConference PDFCodeCode 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="2405.13637")

Code

Syntology Ran 3 of 8 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 1 ran · fixture could not drive it; 2 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

croitorualin/curriculum-dpo officialmentioned in papermentioned on GitHubpytorchNOASSERTION 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

8 samples harvested; 3 ran; 0 honoured the contract we drafted; 5 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.

1ran · fixture could not drive it
2ran
5unverified

Licence: 8 of the 8 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 croitorualin/curriculum-dpo. “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.

get_config croitorualin/curriculum-dpo/config/args_sd.py official repository ran licence not identified · pointer only · cde33670163c2e85 · report
get_module_kohya_state_dict croitorualin/curriculum-dpo/data_generators/generate_data_lcm.py official repository ran licence not identified · pointer only · 1be6fcb325dde58c · report
guidance_scale_embedding croitorualin/curriculum-dpo/train_lcm.py official repository ran · fixture could not drive it no licence file found · pointer only · f1b675952d115b7f · report
collate_fn croitorualin/curriculum-dpo/reward_models/compute_human_score.py official repository unverified licence not identified · pointer only · 968a96d62e5fb816 · report
collate_fn_pairs croitorualin/curriculum-dpo/reward_models/compute_human_score.py official repository unverified licence not identified · pointer only · 96b875ba49ec4098 · report
get_config croitorualin/curriculum-dpo/config/args_lcm.py official repository unverified licence not identified · pointer only · f1633432b4fbd0d6 · report
get_module_kohya_state_dict croitorualin/curriculum-dpo/train_lcm.py official repository unverified no licence file found · pointer only · 4c7c3edd706a5541 · report
import_model_class_from_model_name_or_path croitorualin/curriculum-dpo/train_stablediffusion.py official repository unverified licence not identified · pointer only · 3a3852d78600db34 · 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 DrawBench LCM (Curriculum DPO) Aesthetics (Laion Aesthtetics Predictor) 6.1829 #1 of 8 Archive leaderboard report
Text-to-Image Generation DrawBench LCM (Curriculum DPO) Human Preference Alignement (HPSv2) 0.2851 #1 of 8 Archive leaderboard report
Text-to-Image Generation DrawBench LCM (Curriculum DPO) Text Alignement (SentenceBERT) 0.5812 #1 of 8 Archive leaderboard report
Text-to-Image Generation DrawBench Stable Diffusion 1.5 (Curriculum DPO) Aesthetics (Laion Aesthtetics Predictor) 5.7060 #5 of 8 Archive leaderboard report
Text-to-Image Generation DrawBench Stable Diffusion 1.5 (Curriculum DPO) Human Preference Alignement (HPSv2) 0.2681 #5 of 8 Archive leaderboard report
Text-to-Image Generation DrawBench Stable Diffusion 1.5 (Curriculum DPO) Text Alignement (SentenceBERT) 0.6234 #5 of 8 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

DPO

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