SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2503.09641 · ICCV · 2025

SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation

Song Han, Han Cai, Enze Xie, Sayak Paul, Yuyang Zhao, Shuchen Xue, Jincheng Yu, Junyu Chen, Junsong Chen

arXiv · PDF · Open in the Atlas

Code that ran

10 of 12 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 7 have no contract verdict; 1 failure of our instrument; 2 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/2503.09641.json · badge: /api/ran/2503.09641.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
NVlabs/Sana canonical (classifier label)
classifier basis not recorded on the link
10 ran · 2 no recorded run
FunctionStatusWhere it lives
apply_style Ran
ran on a synthesized input
NVlabs/Sana/app/app_sana.py
pointer only (licence: Apache-2.0) · get_code("2b6d6883dc96127d")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, NVlabs/Sana, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

classify_height_width_bin Ran
ran, honoured the contract we drafted
NVlabs/Sana/app/sana_controlnet_pipeline.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from showlab/DIM, is pointer only (licence: NOASSERTION) · get_code("9d06ee4c83d30c78")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, NVlabs/Sana, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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_greyscale_mask Ran
ran on a synthesized input
NVlabs/Sana/app/app_sana_inpaint.py
pointer only (licence: Apache-2.0) · get_code("a21b14671ce99511")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, NVlabs/Sana, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

get_ar_from_ref_image Ran
ran on a synthesized input
NVlabs/Sana/app/sana_controlnet_pipeline.py
pointer only (licence: Apache-2.0) · get_code("4d4ea6fb407e109b")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, NVlabs/Sana, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

guidance_type_select Ran
ran; our contract draft was wrong, not the code
NVlabs/Sana/app/sana_controlnet_pipeline.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from showlab/DIM, is pointer only (licence: NOASSERTION) · get_code("57e4b02c63e00263")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, NVlabs/Sana, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

hash_str_to_int Ran
ran on a synthesized input
NVlabs/Sana/app/app_sana_4bit_compare_bf16.py
pointer only (licence: Apache-2.0) · get_code("34bc01284508eb93")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, NVlabs/Sana, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

norm_ip Ran
ran on a synthesized input
NVlabs/Sana/app/app_sana_controlnet_hed.py
pointer only (licence: Apache-2.0) · get_code("b3da9990e1ba94e2")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, NVlabs/Sana, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

randomize_seed_fn Ran
ran, honoured the contract we drafted
NVlabs/Sana/app/app_sana_4bit.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Ji4chenLi/t2v-turbo, is pointer only (licence: NONE) · get_code("1c00f3d9c2aa103c")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, NVlabs/Sana, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

save_image Ran
ran on a synthesized input
NVlabs/Sana/app/app_sana_controlnet_hed.py
pointer only (licence: Apache-2.0) · get_code("3b9d90947aa40dd2")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, NVlabs/Sana, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

tensor_to_pil Ran
ran on a synthesized input
NVlabs/Sana/app/sana_pipeline_inpaint.py
pointer only (licence: Apache-2.0) · get_code("01b02ff9e21d4414")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, NVlabs/Sana, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

run_inference Not yet run
unverified (harvested, no recorded run)
NVlabs/Sana/app/app_sana.py
pointer only (licence: Apache-2.0) · get_code("3766af1242aa1f12")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, NVlabs/Sana, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

save_image_sana Not yet run
unverified (harvested, no recorded run)
NVlabs/Sana/app/app_sana_4bit.py
pointer only (licence: Apache-2.0) · get_code("ec6eb00169f04a34")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, NVlabs/Sana, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 3 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 3 later) and 9 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
randomize_seed_fn 4 other papers
3 dated earlier, 1 later
2403.04692 (2024-03)
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation
2403.16627 (2024-03)
SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions
2410.05677 (2024-10)
T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design
and 1 more not named here
classify_height_width_bin 1 other paper
1 later
2509.01986 (2025-09)
Draw-In-Mind: Rebalancing Designer-Painter Roles in Unified Multimodal Models Benefits Image Editing
guidance_type_select 1 other paper
1 later
2509.01986 (2025-09)
Draw-In-Mind: Rebalancing Designer-Painter Roles in Unified Multimodal Models Benefits Image Editing

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

This paper presents SANA-Sprint, an efficient diffusion model for ultra-fast text-to-image (T2I) generation. SANA-Sprint is built on a pre-trained foundation model and augmented with hybrid distillation, dramatically reducing inference steps from 20 to 1-4. We introduce three key innovations: (1) We propose a training-free approach that transforms a pretrained flow-matching model for continuous-time consistency distillation (sCM), eliminating costly training from scratch and achieving high training efficiency. Our hybrid distillation strategy combines sCM with latent adversarial distillation (LADD): sCM ensures alignment with the teacher model, while LADD enhances single-step generation fidelity. (2) SANA-Sprint is a unified step-adaptive model that achieves high-quality generation in 1-4 steps, eliminating step-specific training and improving efficiency. (3) We integrate ControlNet with SANA-Sprint for real-time interactive image generation, enabling instant visual feedback for user interaction. SANA-Sprint establishes a new Pareto frontier in speed-quality tradeoffs, achieving stateof-the-art performance with 7.59 FID and 0.74 GenEval in only 1 step -outperforming FLUX-schnell (7.94 FID / 0.71 GenEval) while being 10! faster (0.1s vs 1.1s on H100). It also achieves 0.1s (T2I) and 0.25s (ControlNet) latency for 1024→1024 images on H100, and 0.31s (T2I) on an RTX 4090, showcasing its exceptional efficiency and potential for AI-powered consumer applications (AIPC). Code and pre-trained models will be open-sourced.

For agents

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

get_harvested_code_for_paper("2503.09641")
get_code_for_paper("2503.09641")
have("2503.09641")

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

curl https://syntology.ai/api/ran/2503.09641.json

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

[![Syntology run record](https://syntology.ai/api/ran/2503.09641.svg)](https://syntology.ai/paper/2503.09641)

Connect an agent — have() is free.