SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.11355 · 2024

Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think

arXiv · PDF · Open in the Atlas

Code that ran

16 of 17 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; 3 honoured the contract we drafted, 2 violated it and 0 have no contract verdict; 11 failures of our instrument; 1 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/2409.11355.json · badge: /api/ran/2409.11355.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
VisualComputingInstitute/diffusion-e2e-ft canonical (classifier label)
classifier basis: census
16 ran · 1 no recorded run
FunctionStatusWhere it lives
compute_scale_and_shift_masked Ran
ran; our contract draft was wrong, not the code
VisualComputingInstitute/diffusion-e2e-ft/training/util/loss.py
pointer only (licence: NONE) · get_code("3b234f415dac393b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualComputingInstitute/diffusion-e2e-ft when it was checked. 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.

define_loss Ran
ran; our contract draft was wrong, not the code
VisualComputingInstitute/diffusion-e2e-ft/DSINE/projects/baseline_normal/losses.py
pointer only (licence: NONE) · get_code("b48c284df8bc63a7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualComputingInstitute/diffusion-e2e-ft when it was checked. 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_r_pitch Ran
ran, honoured the contract we drafted
VisualComputingInstitute/diffusion-e2e-ft/DSINE/utils/rotation.py
pointer only (licence: NONE) · get_code("2c816eedd2f0474c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualComputingInstitute/diffusion-e2e-ft when it was checked. 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_r_roll Ran
ran, honoured the contract we drafted
VisualComputingInstitute/diffusion-e2e-ft/DSINE/utils/rotation.py
pointer only (licence: NONE) · get_code("85d2c7386475ae37")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualComputingInstitute/diffusion-e2e-ft when it was checked. 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_r_yaw Ran
ran, honoured the contract we drafted
VisualComputingInstitute/diffusion-e2e-ft/DSINE/utils/rotation.py
pointer only (licence: NONE) · get_code("14244d03bf3e5f48")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualComputingInstitute/diffusion-e2e-ft when it was checked. 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.

intrins_crop Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
VisualComputingInstitute/diffusion-e2e-ft/DSINE/utils/projection.py
pointer only (licence: NONE) · get_code("07d8c13c1190a20a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualComputingInstitute/diffusion-e2e-ft when it was checked. 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.

intrins_to_zero Ran
ran, violated the contract we drafted
VisualComputingInstitute/diffusion-e2e-ft/DSINE/utils/projection.py
pointer only (licence: NONE) · get_code("1218c2650fe6ffed")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualComputingInstitute/diffusion-e2e-ft when it was checked. 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.

intrins_zero_to Ran
ran, violated the contract we drafted
VisualComputingInstitute/diffusion-e2e-ft/DSINE/utils/projection.py
pointer only (licence: NONE) · get_code("f56119d671b23caa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualComputingInstitute/diffusion-e2e-ft when it was checked. 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.

l1_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
VisualComputingInstitute/diffusion-e2e-ft/DSINE/projects/baseline_normal/losses.py
pointer only (licence: NONE) · get_code("30d6db04f2c86d1d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualComputingInstitute/diffusion-e2e-ft when it was checked. 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.

l2_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
VisualComputingInstitute/diffusion-e2e-ft/DSINE/projects/baseline_normal/losses.py
pointer only (licence: NONE) · get_code("542e39255f62d87e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualComputingInstitute/diffusion-e2e-ft when it was checked. 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.

load_checkpoint Ran
ran; our contract draft was wrong, not the code
VisualComputingInstitute/diffusion-e2e-ft/DSINE/utils/utils.py
pointer only (licence: NONE) · get_code("769dc6d3c6aa40de")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualComputingInstitute/diffusion-e2e-ft when it was checked. 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.

pyramid_noise_like Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
VisualComputingInstitute/diffusion-e2e-ft/GeoWizard/geowizard/models/geowizard_pipeline.py
pointer only (licence: NONE) · get_code("11eeeb13d2957ebf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualComputingInstitute/diffusion-e2e-ft when it was checked. 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.

setup_custom_logger Ran
ran; our contract draft was wrong, not the code
VisualComputingInstitute/diffusion-e2e-ft/DSINE/utils/utils.py
pointer only (licence: NONE) · get_code("dc4ca4a94df3d89e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualComputingInstitute/diffusion-e2e-ft when it was checked. 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_numpy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
VisualComputingInstitute/diffusion-e2e-ft/DSINE/utils/visualize.py
pointer only (licence: NONE) · get_code("e4738f6dce471506")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualComputingInstitute/diffusion-e2e-ft when it was checked. 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.

txt_to_list Ran
ran; our contract draft was wrong, not the code
VisualComputingInstitute/diffusion-e2e-ft/DSINE/utils/utils.py
pointer only (licence: NONE) · get_code("2324fc8ae05d9f6d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualComputingInstitute/diffusion-e2e-ft when it was checked. 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.

unnormalize Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
VisualComputingInstitute/diffusion-e2e-ft/DSINE/utils/visualize.py
pointer only (licence: NONE) · get_code("61cf14e229883558")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualComputingInstitute/diffusion-e2e-ft when it was checked. 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.

normal_to_rgb Not yet run
unverified (harvested, no recorded run)
VisualComputingInstitute/diffusion-e2e-ft/DSINE/utils/visualize.py
pointer only (licence: NONE) · get_code("774236d466c851a3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, VisualComputingInstitute/diffusion-e2e-ft when it was checked. 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 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 3 the same month, 0 later) and 14 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
intrins_crop 1 other paper
1 the same month
2409.18124 (2024-09)
Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction
intrins_to_zero 1 other paper
1 the same month
2409.18124 (2024-09)
Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction
intrins_zero_to 1 other paper
1 the same month
2409.18124 (2024-09)
Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction

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

Recent work showed that large diffusion models can be reused as highly precise monocular depth estimators by casting depth estimation as an image-conditional image generation task. While the proposed model achieved state-of-the-art results, high computational demands due to multi-step inference limited its use in many scenarios. In this paper, we show that the perceived inefficiency was caused by a flaw in the inference pipeline that has so far gone unnoticed. The fixed model performs comparably to the best previously reported configuration while being more than 200$\times$ faster. To optimize for downstream task performance, we perform end-to-end fine-tuning on top of the single-step model with task-specific losses and get a deterministic model that outperforms all other diffusion-based depth and normal estimation models on common zero-shot benchmarks. We surprisingly find that this fine-tuning protocol also works directly on Stable Diffusion and achieves comparable performance to current state-of-the-art diffusion-based depth and normal estimation models, calling into question some of the conclusions drawn from prior works.

For agents

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

get_harvested_code_for_paper("2409.11355")
get_code_for_paper("2409.11355")
have("2409.11355")

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

curl https://syntology.ai/api/ran/2409.11355.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.11355.svg)](https://syntology.ai/paper/2409.11355)

Connect an agent — have() is free.