Papers › Flow-Anchored Consistency Models

Flow-Anchored Consistency Models

4 Jul 2025arXiv:2507.03738archive 2025-07-28

Yansong Peng, Kai Zhu, Yu Liu, Pingyu Wu, Hebei Li, Xiaoyan Sun, Feng Wu

Continuous-time Consistency Models (CMs) promise efficient few-step generation but face significant challenges with training instability. We argue this instability stems from a fundamental conflict: by training a network to learn only a shortcut across a probability flow, the model loses its grasp on the instantaneous velocity field that defines the flow. Our solution is to explicitly anchor the model in the underlying flow during training. We introduce the Flow-Anchored Consistency Model (FACM), a simple but effective training strategy that uses a Flow Matching (FM) task as an anchor for the primary CM shortcut objective. This Flow-Anchoring approach requires no architectural modifications and is broadly compatible with standard model architectures. By distilling a pre-trained LightningDiT model, our method achieves a state-of-the-art FID of 1.32 with two steps (NFE=2) and 1.76 with just one step (NFE=1) on ImageNet 256x256, significantly outperforming previous methods. This provides a general and effective recipe for building high-performance, few-step generative models. Our code and pretrained models: https://github.com/ali-vilab/FACM.

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="2507.03738")

Code

Syntology Ran 8 of 14 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 4 ran · our draft was wrong; 2 ran · fixture could not drive it.

By repository: official repository: 14 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ali-vilab/FACM officialmentioned in papermentioned on GitHubpytorchApache-2.0 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

14 samples harvested; 8 ran; 1 honoured the contract we drafted; 6 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
1ran · violated contract
4ran · our draft was wrong
2ran · fixture could not drive it
6unverified

Licence: 0 of the 14 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 ali-vilab/FACM. “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.

Normalize ali-vilab/FACM/ldit/autoencoder.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 9fcdaa6e423e8aa7 · report
apply_rotary_emb ali-vilab/FACM/ldit/rmsnorm.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · d7b6dcfe63bfe59b · report
broadcat ali-vilab/FACM/ldit/pos_embed.py official repository ran · honoured contract Apache-2.0 (permissive) · f50a8d20efb35c68 · report
center_crop_arr ali-vilab/FACM/ldit/autoencoder.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 1712a07966b542ee · report
nonlinearity ali-vilab/FACM/ldit/autoencoder.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 3137073275f8c21a · report
precompute_freqs_cis ali-vilab/FACM/ldit/rmsnorm.py official repository ran · violated contract Apache-2.0 (permissive) · 04a1fa63d6d4b8e4 · report
reshape_for_broadcast ali-vilab/FACM/ldit/rmsnorm.py official repository ran · fixture could not drive it Apache-2.0 (permissive) · 5a639d78ada17fee · report
rotate_half ali-vilab/FACM/ldit/pos_embed.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 58823d9435a8751b · report
apply_classifier_free_guidance ali-vilab/FACM/sampler.py official repository unverified Apache-2.0 (permissive) · d7165e1d0b3125c8 · report
apply_timestep_shift ali-vilab/FACM/sampler.py official repository unverified Apache-2.0 (permissive) · b23287fcefddccc7 · report
modulate ali-vilab/FACM/ldit/lightningdit.py official repository unverified Apache-2.0 (permissive) · 12924cbdbc48113b · report
pixel_norm ali-vilab/FACM/ldit/lightningdit.py official repository unverified Apache-2.0 (permissive) · 4ffded33c11b4d7f · report
prepare_model_input ali-vilab/FACM/sampler.py official repository unverified Apache-2.0 (permissive) · 3a089f03249495cb · report
scm_modulate ali-vilab/FACM/ldit/lightningdit.py official repository unverified Apache-2.0 (permissive) · ff2d71bfa2bbd54d · report

Tasks

Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation ImageNet 256x256 FACM (2-step) FID 1.32 #10 of 94 Archive leaderboard report
Image Generation ImageNet 256x256 FACM (2-step) NFE 2 #10 of 94 Archive leaderboard report
Image Generation ImageNet 256x256 FACM (1-step) FID 1.70 #32 of 94 Archive leaderboard report
Image Generation ImageNet 256x256 FACM (1-step) NFE 1 #32 of 94 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Consistency Models

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