Methods › Computer Vision › Generative Models › Self-Attention Guidance
Self-Attention Guidance
Introduced by Susung Hong et al. in Improving Sample Quality of Diffusion Models Using Self-Attention Guidance
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
The archive carries no description for this method.
In Syntology for a different name, 'self-guidance', about another paper, arXiv:2410.13136: repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: official). The lookup matched a different name in Syntology's graph, 'self-guidance' (resolution: token_match); this answer is about that name. About another paper: this answer is about arXiv:2410.13136, while the archive credits arXiv:2210.00939.
Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.
- S2-Guidance · shares_name_tokens (shares name tokens with this name; a different method) · level V2 · retrieve with
get_reference_implementation(name='S2-Guidance') - SELF-REDTEAM · shares_name_tokens (shares name tokens with this name; a different method) · level V2 · retrieve with
get_reference_implementation(name='SELF-REDTEAM') - Loop Guidance · shares_name_tokens (shares name tokens with this name; a different method) · level V2 · retrieve with
get_reference_implementation(name='Loop Guidance') - RPC-Attention · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='RPC-Attention') - Slot Attention · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Slot Attention') - Primal-Attention · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='Primal-Attention')
Origin paper of this answer, arXiv:2410.13136 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 11 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 11 where Syntology's instrument failed) · 1 unverified (of 12 harvested samples) · 8 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 7 · with a code link: 6 · where Syntology ran a sample: 2 (2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (2 of 7 tagged: 2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 7 of 7, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
DC-VSR: Spatially and Temporally Consistent Video Super-Resolution with Video Diffusion Prior 5 Feb 2025 · 0 repositories · arXiv:2502.03502
-
SketchDeco: Decorating B&W Sketches with Colour 29 May 2024 · 1 repository · arXiv:2405.18716
-
CSTA: CNN-based Spatiotemporal Attention for Video Summarization 20 May 2024 · 1 repository · arXiv:2405.11905Syntology official (archive's flag): 7 ran · 7 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 7 samples that ran constructed an object rather than computing a result (of 8 harvested samples)
-
A New Multi-Picture Architecture for Learned Video Deinterlacing and Demosaicing with Parallel Deformable Convolution and Self-Attention Blocks 19 Apr 2024 · 1 repository · arXiv:2404.13018
-
TexTile: A Differentiable Metric for Texture Tileability 19 Mar 2024 · 1 repository · arXiv:2403.12961
-
PPSURF: Combining Patches and Point Convolutions for Detailed Surface Reconstruction 16 Jan 2024 · 1 repository · arXiv:2401.08518
-
Improving Sample Quality of Diffusion Models Using Self-Attention Guidance 3 Oct 2022 · 5 repositories · arXiv:2210.00939Syntology official (archive's flag): 16 ran · 19 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 2 violated, 1 with no contract checked; 13 where Syntology's instrument failed) · 3 unverified (of 22 harvested samples) · 20 pointer-only (licence)
Tasks archive 2025-07-28
17 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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