Papers › Interpreting the Weight Space of Customized Diffusion Models

Interpreting the Weight Space of Customized Diffusion Models

13 Jun 2024arXiv:2406.09413archive 2025-07-28

Amil Dravid, Yossi Gandelsman, Kuan-Chieh Wang, Rameen Abdal, Gordon Wetzstein, Alexei A. Efros, Kfir Aberman

We investigate the space of weights spanned by a large collection of customized diffusion models. We populate this space by creating a dataset of over 60,000 models, each of which is a base model fine-tuned to insert a different person's visual identity. We model the underlying manifold of these weights as a subspace, which we term weights2weights. We demonstrate three immediate applications of this space that result in new diffusion models -- sampling, editing, and inversion. First, sampling a set of weights from this space results in a new model encoding a novel identity. Next, we find linear directions in this space corresponding to semantic edits of the identity (e.g., adding a beard), resulting in a new model with the original identity edited. Finally, we show that inverting a single image into this space encodes a realistic identity into a model, even if the input image is out of distribution (e.g., a painting). We further find that these linear properties of the diffusion model weight space extend to other visual concepts. Our results indicate that the weight space of fine-tuned diffusion models can behave as an interpretable meta-latent space producing new models.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2406.09413")

Code

Syntology Ran 4 of 8 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · honoured contract; 3 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

snap-research/weights2weights officialmentioned in papermentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

8 samples harvested; 4 ran; 1 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
3ran
4unverified

Licence: 8 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from snap-research/weights2weights. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “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.

Each sample ends with its 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.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at 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 label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

b2mb snap-research/weights2weights/train_dreambooth.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · 32380a050ca033d4 · report
debias snap-research/weights2weights/editing.py official repository ran licence not identified · pointer only · 6015ab268a8c8cec · report
get_direction snap-research/weights2weights/editing.py official repository ran licence not identified · pointer only · 7e175f3d5a77d724 · report
inference snap-research/weights2weights/utils.py official repository ran licence not identified · pointer only · ddb9257aed90e222 · report
edit_inference snap-research/weights2weights/editing.py official repository unverified licence not identified · pointer only · 1614dd4e41f6caec · report
import_model_class_from_model_name_or_path snap-research/weights2weights/train_dreambooth.py official repository unverified no licence file found · pointer only · 2f00b39db5a81466 · report
invert snap-research/weights2weights/inversion.py official repository unverified licence not identified · pointer only · a1b7c201b4b5e735 · report
parse_args snap-research/weights2weights/train_dreambooth.py official repository unverified licence not identified · pointer only · f5bc09ecb185eb8d · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

BASEDiffusionSET

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