Home › Code › retrieve_timesteps

retrieve_timesteps

Syntologyentry name in harvested coderead from the graph 2026-09-24

retrieve_timesteps appears in the code Syntology harvested for 70 papers, as 28 distinct code bodies found in 80 places (a place is one code body under one paper). At least one of them ran in 61 of the papers; 0 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named retrieve_timesteps do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 17 of the 28 distinct code bodies named retrieve_timesteps; 11 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
9ran · our draft was wrong
0ran · fixture could not drive it
8ran
11unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 34 of the 80 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “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, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

70 papers shown of 70, newest first; 80 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 17 papers added by Syntology; 4 papers have no page here and are shown by arXiv id only. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's 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.

PaperDateFileStatus SyntologyLicence
Fill My Mirror: Geometry-Constrained Mirror Inpainting added by Syntology 2026-09 (from id) OfekBasson/Fill-My-Mirror/fill_my_mirror/dual_mask_inpainting/pipeline_flux1.py 39dfd0bc34e28e1f unverified MIT (permissive)
Dotting the Eye: An Intent-Driven Image Retouching Agent for Visual Focus Enhancement added by Syntology 2026-09 (from id) DragonisCV/EyeControl/src/pipelines/training_pipeline.py 0b56680ee1708fee ran · our draft was wrong no licence file found · pointer only
The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL added by Syntology 2026-06 (from id) microsoft/soc-fine-tuning-sd/src/soc_pipeline_sd.py 0b56680ee1708fee ran · our draft was wrong MIT (permissive)
Rethinking Dataset Distillation for Classification: Do Distilled Sets Outperform Coresets? added by Syntology 2026-06 (from id) jachansantiago/mode_guidance/diffusers/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_mode_guidance.py 0b56680ee1708fee ran · our draft was wrong no licence file found · pointer only
CAB: Accelerating Flow and Diffusion Sampling via Rectification and Corrected Adams-Bashforth added by Syntology 2026-05 (from id) Anuska-Roy/CAB/pipeline_qwenimage.py 0b56680ee1708fee ran · our draft was wrong no licence file found · pointer only
Diagnosing and Correcting Concept Omission in Multimodal Diffusion Transformers added by Syntology 2026-05 (from id) KangHyun-dsail/OSI/flux_osi_modules/pipeline.py 3bc16dac88aab75d ran no licence file found · pointer only
Diagnosing and Correcting Concept Omission in Multimodal Diffusion Transformers added by Syntology 2026-05 (from id) KangHyun-dsail/OSI/sd3_osi_modules/pipeline.py ce250dea9fb7bde7 ran no licence file found · pointer only
Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation added by Syntology 2026-04 (from id) iguoyanjun/Memorize-When-Needed/pipeline.py 22b1f260da28f6a5 ran · our draft was wrong no licence file found · pointer only
Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation added by Syntology 2026-04 (from id) iguoyanjun/Memorize-When-Needed/models/utils/fm_solvers.py 3eeae6ab9b822c6c unverified no licence file found · pointer only
RoamScene3D: Immersive Text-to-3D Scene Generation via Adaptive Object-aware Roaming added by Syntology 2026-01 (from id) JS-CHU/RoamScene3D/src/pipeline_flux.py 0b56680ee1708fee ran · our draft was wrong no licence file found · pointer only
Task-Oriented Data Synthesis and Control-Rectify Sampling for Remote Sensing Semantic Segmentation added by Syntology 2025-12 (from id) Yunkai-Yang/crfm/src/utils/crfm.py 3824ef7a8074b09e ran · our draft was wrong no licence file found · pointer only
Training-Free Safe Text Embedding Guidance for Text-to-Image Diffusion Models added by Syntology 2025-10 (from id) aailab-kaist/STG/pipelines/pipeline_stable_diffusion_stg.py 0b56680ee1708fee ran · our draft was wrong Apache-2.0 (permissive)
ReCon: Region-Controllable Data Augmentation with Rectification and Alignment for Object Detection added by Syntology 2025-10 (from id) haoweiz23/ReCon/pipelines/pipeline_controlnet_recon.py 63e7d99da5ea137f ran · our draft was wrong no licence file found · pointer only
ConceptSplit: Decoupled Multi-Concept Personalization of Diffusion Models via Token-wise Adaptation and Attention Disentanglement added by Syntology 2025-10 (from id) KU-VGI/ConceptSplit/pipeline_sdxl_loda.py f3a81898d239b163 ran · our draft was wrong MIT (permissive)
Knowledge Distillation Detection for Open-weights Models added by Syntology 2025-10 (from id) identical code first harvested elsewhere 0b56680ee1708fee ran · our draft was wrong licence of this copy not recorded
Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling added by Syntology 2025-09 (from id) enyac-group/q-sched/src/lcm/lcm_pipeline.py 0b56680ee1708fee ran · our draft was wrong BSD-3-Clause (permissive)
GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors added by Syntology 13 Aug 2025 GVCLab/GSFixer/Reconstruction/gsfixer/cogvideo/pipeline_cogvideox_video2video_control.py 22b1f260da28f6a5 ran · our draft was wrong no licence file found · pointer only
InstantEdit: Text-Guided Few-Step Image Editing with Piecewise Rectified Flow added by Syntology 2025-08 (from id) Supercomputing-System-AI-Lab/InstantEdit/src/pipeline.py 3338a5b299ea25ec ran · our draft was wrong no licence file found · pointer only
SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering added by Syntology 2025-08 (from id) AMAAI-Lab/SonicMaster/model.py 59b1e128b0f382eb unverified Apache-2.0 (permissive)
arXiv:2507.10225 2025-07 (from id) Jarvisgivemeasuit/SynOOD/diffusion_inpainting_pipeline.py 0b56680ee1708fee ran · our draft was wrong Apache-2.0 (permissive)
T-LoRA: Single Image Diffusion Model Customization Without Overfitting 8 Jul 2025 controlgenai/t-lora/tlora/model/pipeline_sdxl.py acbd51a8798254c2 unverified MIT (permissive)
Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details 19 Jun 2025 tencent/hunyuan3d-2/hy3dgen/shapegen/pipelines.py 607a22f436cb1076 unverified licence not identified · pointer only
Token Perturbation Guidance for Diffusion Models 10 Jun 2025 taatiteam/token-perturbation-guidance/pipeline_sdxl_tpg.py 5817cdfd5ceed6f4 ran · our draft was wrong MIT (permissive)
Latent Wavelet Diffusion: Enabling 4K Image Synthesis for Free 31 May 2025 LuigiSigillo/LatentWaveletDiffusion/src/pipeline_flux.py 0b56680ee1708fee ran · our draft was wrong Apache-2.0 (permissive)
OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation 26 May 2025 PKU-YuanGroup/ConsisID/models/pipeline_consisid.py 22b1f260da28f6a5 ran · our draft was wrong Apache-2.0 (permissive)
Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis 15 May 2025 tang-bd/fuse-dit/diffusion/pipelines.py 0582c403b48a1d8d unverified Apache-2.0 (permissive)
HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation 7 May 2025 identical code first harvested elsewhere f3a81898d239b163 ran · our draft was wrong licence of this copy not recorded
HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance 8 Apr 2025 Bujiazi/HiFlow/flux_pipeline_hiflow.py 6d81be4629500481 unverified Apache-2.0 (permissive)
A Unified Image-Dense Annotation Generation Model for Underwater Scenes 27 Mar 2025 hongklin/tide/tide/pipeline/pipeline_tide.py 5e49900a73989947 unverified Apache-2.0 (permissive)
InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity 20 Mar 2025 bytedance/InfiniteYou/pipelines/pipeline_flux_infusenet.py 22b1f260da28f6a5 ran · our draft was wrong Apache-2.0 (permissive)
EEdit: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing 13 Mar 2025 yuriyanzexuan/eedit/MyCodes/MyFluxCompositionPipeline.py 0b56680ee1708fee ran · our draft was wrong MIT (permissive)
FantasyID: Face Knowledge Enhanced ID-Preserving Video Generation 2025-02 (from id) Fantasy-AMAP/fantasy-id/models/pipeline_cogvideox.py 22b1f260da28f6a5 ran · our draft was wrong Apache-2.0 (permissive)
Light-A-Video: Training-free Video Relighting via Progressive Light Fusion 12 Feb 2025 bcmi/Light-A-Video/src/ic_light_pipe.py 3338a5b299ea25ec ran · our draft was wrong Apache-2.0 (permissive)
TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models 10 Feb 2025 VAST-AI-Research/TripoSG/triposg/pipelines/pipeline_triposg.py 22b1f260da28f6a5 ran · our draft was wrong MIT (permissive)
SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders 29 Jan 2025 cywinski/saeuron/SAE/utils.py 77ce5b8dcbc5200c unverified Apache-2.0 (permissive)
Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models 14 Jan 2025 Vchitect/Vchitect-2.0/models/pipeline.py 0b56680ee1708fee ran · our draft was wrong Apache-2.0 (permissive)
Ingredients: Blending Custom Photos with Video Diffusion Transformers 3 Jan 2025 feizc/ingredients/models/pipeline_cogvideox.py 22b1f260da28f6a5 ran · our draft was wrong Apache-2.0 (permissive)
Dual Diffusion for Unified Image Generation and Understanding 31 Dec 2024 zijieli-Jlee/Dual-Diffusion/sd3_modules/dual_diff_pipeline.py 0b56680ee1708fee ran · our draft was wrong MIT (permissive)
CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up 20 Dec 2024 huage001/clear/pipeline_flux_img2img.py 0b56680ee1708fee ran · our draft was wrong Apache-2.0 (permissive)
HunyuanVideo: A Systematic Framework For Large Video Generative Models 3 Dec 2024 tencent-hunyuan/hunyuanvideo/hyvideo/diffusion/pipelines/pipeline_hunyuan_video.py f3a81898d239b163 ran · our draft was wrong licence not identified · pointer only
OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows 2 Dec 2024 jacklishufan/omniflows/omniflow/pipelines/omniflow_pipeline.py 0b56680ee1708fee ran · our draft was wrong no licence file found · pointer only
Stable Flow: Vital Layers for Training-Free Image Editing 21 Nov 2024 snap-research/stable-flow/src/diffusers/pipelines/controlnet_sd3/pipeline_stable_diffusion_3_controlnet.py 22b1f260da28f6a5 ran · our draft was wrong no licence file found · pointer only
Stable Flow: Vital Layers for Training-Free Image Editing 21 Nov 2024 snap-research/stable-flow/src/diffusers/pipelines/aura_flow/pipeline_aura_flow.py d32228909732c0bc unverified licence not identified · pointer only
UrbanDiT: A Foundation Model for Open-World Urban Spatio-Temporal Learning 19 Nov 2024 tsinghua-fib-lab/UrbanDiT/src/validation.py 572665172cac0917 unverified MIT (permissive)
Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement 10 Nov 2024 identical code first harvested elsewhere 0b56680ee1708fee ran · our draft was wrong licence of this copy not recorded
Training-free Regional Prompting for Diffusion Transformers 4 Nov 2024 identical code first harvested elsewhere 0b56680ee1708fee ran · our draft was wrong licence of this copy not recorded
Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance 29 Oct 2024 identical code first harvested elsewhere 63e7d99da5ea137f ran · our draft was wrong licence of this copy not recorded
Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance 29 Oct 2024 krafton-ai/Rare-to-Frequent/R2F_Diffusion_sd3.py 0b56680ee1708fee ran · our draft was wrong no licence file found · pointer only
PUMA: Empowering Unified MLLM with Multi-granular Visual Generation 17 Oct 2024 rongyaofang/puma/image_to_image_pipeline_cfg.py ab6808194dea1a0f ran Apache-2.0 (permissive)
MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion 10 Oct 2024 CandleLabAI/MotionAura-ICLR-2025/src/diffusers/pipelines/motionaura/pipeline_motionaura.py 22b1f260da28f6a5 ran · our draft was wrong Apache-2.0 (permissive)
Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow 9 Oct 2024 g-u-n/rectified-diffusion/pipeline.py 3338a5b299ea25ec ran · our draft was wrong no licence file found · pointer only
IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation 9 Oct 2024 yangling0818/rpg-diffusionmaster/RegionalDiffusion_xl.py 63e7d99da5ea137f ran · our draft was wrong MIT (permissive)
IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation 9 Oct 2024 yangling0818/rpg-diffusionmaster/RegionalDiffusion_base.py 6cccd001a059f194 ran MIT (permissive)
PerCo (SD): Open Perceptual Compression 30 Sep 2024 Nikolai10/PerCo/src/pipeline_sd_perco.py 3338a5b299ea25ec ran · our draft was wrong Apache-2.0 (permissive)
Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Function 30 Sep 2024 I2-Multimedia-Lab/Magnet/pipeline_sdxl.py 35717b791550ecb2 ran no licence file found · pointer only
Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction 26 Sep 2024 envision-research/lotus/pipeline.py 6cccd001a059f194 ran Apache-2.0 (permissive)
MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuning 20 Aug 2024 haoningwu3639/MegaFusion/ControlNet-MegaFusion/model/pipeline_controlnet.py 22b1f260da28f6a5 ran · our draft was wrong no licence file found · pointer only
MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuning 20 Aug 2024 haoningwu3639/MegaFusion/SD3-MegaFusion/model/pipeline.py 9ecc0ef42d51e6b9 ran no licence file found · pointer only
ControlNeXt: Powerful and Efficient Control for Image and Video Generation 12 Aug 2024 dvlab-research/controlnext/ControlNeXt-SD1.5/models/pipeline_controlnext.py 35717b791550ecb2 ran Apache-2.0 (permissive)
EasyInv: Toward Fast and Better DDIM Inversion 9 Aug 2024 potato-kitty/EasyInv/EasyInv_SDXL/utils.py 68b3877c0415eb29 ran MIT (permissive)
Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention 1 Aug 2024 susunghong/seg-sdxl/pipeline_seg.py 63e7d99da5ea137f ran · our draft was wrong no licence file found · pointer only
Tora: Trajectory-oriented Diffusion Transformer for Video Generation 31 Jul 2024 alibaba/Tora/diffusers-version/tora/i2v_pipeline.py 22b1f260da28f6a5 ran · our draft was wrong Apache-2.0 (permissive)
FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds 1 Jul 2024 open-mmlab/foleycrafter/foleycrafter/pipelines/pipeline_controlnet.py 35717b791550ecb2 ran Apache-2.0 (permissive)
DiffuseHigh: Training-free Progressive High-Resolution Image Synthesis through Structure Guidance 26 Jun 2024 yhyun225/DiffuseHigh/pipeline_diffusehigh_sdxl.py 35717b791550ecb2 ran MIT (permissive)
Is One GPU Enough? Pushing Image Generation at Higher-Resolutions with Foundation Models 11 Jun 2024 thanos-db/pixelsmith/pixelsmith_pipeline.py f38889775adae791 ran · our draft was wrong GPL-3.0 (copyleft) · pointer only
ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization 6 Jun 2024 ExplainableML/ReNO/models/RewardFlux.py 0b56680ee1708fee ran · our draft was wrong MIT (permissive)
ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization 6 Jun 2024 ExplainableML/ReNO/models/RewardStableDiffusion.py 6c337532224391b0 ran MIT (permissive)
EasyAnimate: A High-Performance Long Video Generation Method based on Transformer Architecture 29 May 2024 aigc-apps/easyanimate/easyanimate/pipeline/pipeline_easyanimate.py 2b5cdb1b9cbb963c ran · our draft was wrong Apache-2.0 (permissive)
AID: Attention Interpolation of Text-to-Image Diffusion 26 Mar 2024 qy-h00/attention-interpolation-diffusion/gradio_src/pipeline_interpolated_sd.py 3338a5b299ea25ec ran · our draft was wrong no licence file found · pointer only
AID: Attention Interpolation of Text-to-Image Diffusion 26 Mar 2024 qy-h00/attention-interpolation-diffusion/gradio_src/pipeline_interpolated_sdxl.py 35717b791550ecb2 ran no licence file found · pointer only
BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion 11 Mar 2024 tencentarc/brushnet/src/diffusers/pipelines/brushnet/pipeline_brushnet.py 35717b791550ecb2 ran no licence file found · pointer only
Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation 16 Feb 2024 guolanqing/self-cascade/source_override/pipeline_sdxl.py 22b1f260da28f6a5 ran · our draft was wrong no licence file found · pointer only
Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs 22 Jan 2024 YangLing0818/RPG-DiffusionMaster/RegionalDiffusion_xl.py 63e7d99da5ea137f ran · our draft was wrong MIT (permissive)
Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs 22 Jan 2024 YangLing0818/RPG-DiffusionMaster/RegionalDiffusion_base.py 6cccd001a059f194 ran MIT (permissive)
PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding 7 Dec 2023 TencentARC/PhotoMaker/photomaker/pipeline_controlnet.py 22b1f260da28f6a5 ran · our draft was wrong no licence file found · pointer only
Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models 10 Oct 2023 tencent-ailab/PCDMs/src/pipelines/PCDMs_pipeline.py 3338a5b299ea25ec ran · our draft was wrong Apache-2.0 (permissive)
arXiv:openreview_YKamMflrv7 G-U-N/UniRL/unimodel/qwenkontext/fluxkontext_pipeline.py 0b56680ee1708fee ran · our draft was wrong Apache-2.0 (permissive)
arXiv:openreview_47JZSOkw5C bxuanz/SigMa/flux/pipeline_flux.py 0b56680ee1708fee ran · our draft was wrong MIT (permissive)
arXiv:Duan_UNIC-Adapter_Unified_Image-instruction_Adapter_with_Multi-modal_Transformer_for_Image_Generation_CVPR_2025_paper unity-research/IP-Adapter-Instruct/ip_adapter/pipeline_stable_diffusion_extra_cfg.py 0b56680ee1708fee ran · our draft was wrong Apache-2.0 (permissive)
arXiv:Duan_UNIC-Adapter_Unified_Image-instruction_Adapter_with_Multi-modal_Transformer_for_Image_Generation_CVPR_2025_paper unity-research/IP-Adapter-Instruct/ip_adapter/pipeline_stable_diffusion_sdxl_extra_cfg.py 22b1f260da28f6a5 ran · our draft was wrong Apache-2.0 (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the 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 cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

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