SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.09556 · ICCV · 2023

Efficient Diffusion Training via Min-SNR Weighting Strategy

Xin Geng, Jianmin Bao, Han Hu, Dong Chen, Chen Li, Baining Guo, Shuyang Gu, Tiankai Hang

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 0 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/2303.09556.json · badge: /api/ran/2303.09556.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
gohyojun15/ANT_diffusion community
Papers with Code archive
1 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
TiankaiHang/Min-SNR-Diffusion-Training community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
GaussianDiffusion Ran
ran on a synthesized input · constructed an object; no result was computed
gohyojun15/ANT_diffusion/diffusion/gaussian_diffusion.py
code served (permissive licence) · get_code("fa87f41839c33df3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, GaussianDiffusion: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch as th
import numpy as np
from enum import auto

# Set random seed for reproducibility
th.manual_seed(0)

# Define the enums locally (since they're part of the function setup)
class LossType:
    MSE = "MSE"
    RESCALED_MSE = "RESCALED_MSE"
    KL = "KL"
    RESCALED_KL = "RESCALED_KL"

class ModelMeanType:
    PREVIOUS_X = "PREVIOUS_X"
    START_X = "START_X"
    EPSILON = "EPSILON"

class ModelVarType:
    LEARNED = "LEARNED"
    FIXED_SMALL = "FIXED_SMALL"
    FIXED_LARGE = "FIXED_LARGE"
    LEARNED_RANGE = "LEARNED_RANGE"

# Create betas: a 1-D numpy array of positive values between 0 and 1
# Typical linear schedule for diffusion
num_timesteps = 10
betas = np.linspace(0.0001, 0.02, num_timesteps, dtype=np.float64)

# Set up the arguments dictionary
ARGS = {
    "betas": betas,
    "model_mean_type": ModelMeanType.EPSILON,
    "model_var_type": ModelVarType.LEARNED,
    "loss_type": LossType.MSE,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type GaussianDiffusion — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a GaussianDiffusion output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
betas_for_alpha_bar Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from NVlabs/DiffPure
pointer only; the stored copy get_code serves, from NVlabs/DiffPure, is pointer only (licence: NOASSERTION) · get_code("2ab2316ac6fdd869")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for 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_snr Ran
ran, honoured the contract we drafted
TiankaiHang/Min-SNR-Diffusion-Training/guided_diffusion/gaussian_diffusion.py
pointer only (licence: NONE) · get_code("66663f07c2ff1d4c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TiankaiHang/Min-SNR-Diffusion-Training 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.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 2 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
betas_for_alpha_bar
brick of this paper's assembly: helper
92 other papers
32 dated earlier, 4 the same month, 54 later, 2 same year, order not determinable · 3 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2102.09672 (2021-02)
Improved Denoising Diffusion Probabilistic Models
and 89 more not named here

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

Denoising diffusion models have been a mainstream approach for image generation, however, training these models often suffers from slow convergence. In this paper, we discovered that the slow convergence is partly due to conflicting optimization directions between timesteps. To address this issue, we treat the diffusion training as a multi-task learning problem, and introduce a simple yet effective approach referred to as Min-SNR-γ. This method adapts loss weights of timesteps based on clamped signal-to-noise ratios, which effectively balances the conflicts among timesteps. Our results demonstrate a significant improvement in converging speed, 3.4× faster than previous weighting strategies. It is also more effective, achieving a new record FID score of 2.06 on the Ima-geNet 256 × 256 benchmark using smaller architectures than that employed in previous state-of-the-art. The code is available at https://github.com/TiankaiHang/Min-SNR-Diffusion-Training.

For agents

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

get_harvested_code_for_paper("2303.09556")
get_code_for_paper("2303.09556")
have("2303.09556")

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

curl https://syntology.ai/api/ran/2303.09556.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.09556.svg)](https://syntology.ai/paper/2303.09556)

Connect an agent — have() is free.