Papers › FreeTraj: Tuning-Free Trajectory Control in Video Diffusion Models

FreeTraj: Tuning-Free Trajectory Control in Video Diffusion Models

24 Jun 2024arXiv:2406.16863archive 2025-07-28

Haonan Qiu, Zhaoxi Chen, Zhouxia Wang, Yingqing He, Menghan Xia, Ziwei Liu

Diffusion model has demonstrated remarkable capability in video generation, which further sparks interest in introducing trajectory control into the generation process. While existing works mainly focus on training-based methods (e.g., conditional adapter), we argue that diffusion model itself allows decent control over the generated content without requiring any training. In this study, we introduce a tuning-free framework to achieve trajectory-controllable video generation, by imposing guidance on both noise construction and attention computation. Specifically, 1) we first show several instructive phenomenons and analyze how initial noises influence the motion trajectory of generated content. 2) Subsequently, we propose FreeTraj, a tuning-free approach that enables trajectory control by modifying noise sampling and attention mechanisms. 3) Furthermore, we extend FreeTraj to facilitate longer and larger video generation with controllable trajectories. Equipped with these designs, users have the flexibility to provide trajectories manually or opt for trajectories automatically generated by the LLM trajectory planner. Extensive experiments validate the efficacy of our approach in enhancing the trajectory controllability of video diffusion 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="2406.16863")

Code

Syntology Ran 11 of 15 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 2 ran · honoured contract; 1 ran · violated contract; 2 ran · our draft was wrong; 6 ran with no contract checked.

By repository: official repository: 15 samples from 1 repository, 11 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

arthur-qiu/freetraj 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

15 samples harvested; 11 ran; 2 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.

2ran · honoured contract
1ran · violated contract
2ran · our draft was wrong
6ran
4unverified

Licence: 0 of the 15 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 arthur-qiu/freetraj. “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.

disabled_train arthur-qiu/freetraj/lvdm/basics.py official repository ran · violated contract Apache-2.0 (permissive) · 4cb732f513d69dfd · report
extract_into_tensor arthur-qiu/freetraj/lvdm/common.py official repository ran · our draft was wrong Apache-2.0 (permissive) · a15cfd7932844ef9 · report
gaussian_weight arthur-qiu/freetraj/lvdm/modules/attention_freetraj.py official repository ran Apache-2.0 (permissive) · e6377402126843ad · report
get_longpath arthur-qiu/freetraj/utils/utils_freetraj.py official repository ran Apache-2.0 (permissive) · f6af12946c26fb35 · report
get_path arthur-qiu/freetraj/utils/utils_freetraj.py official repository ran Apache-2.0 (permissive) · ad6523848b3dc3e2 · report
make_beta_schedule arthur-qiu/freetraj/lvdm/models/utils_diffusion.py official repository ran · honoured contract Apache-2.0 (permissive) · c984209a2c66afbe · report
make_ddim_timesteps arthur-qiu/freetraj/lvdm/models/utils_diffusion.py official repository ran · honoured contract Apache-2.0 (permissive) · 0ea4e960ea54514c · report
normal_kl arthur-qiu/freetraj/lvdm/distributions.py official repository ran fingerprinted Apache-2.0 (permissive) · 17eb0a31c91b671c · report
plan_path arthur-qiu/freetraj/utils/utils_freetraj.py official repository ran Apache-2.0 (permissive) · a7e2f425fa36d893 · report
timestep_embedding arthur-qiu/freetraj/lvdm/models/utils_diffusion.py official repository ran Apache-2.0 (permissive) · 2203f9d1be3dc36c · report
zero_module arthur-qiu/freetraj/lvdm/basics.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 129b804760b3115f · report
autocast arthur-qiu/freetraj/lvdm/common.py official repository unverified Apache-2.0 (permissive) · 32af1c12fd826ef2 · report
gather_data arthur-qiu/freetraj/lvdm/common.py official repository unverified Apache-2.0 (permissive) · b72d8eb89fd75383 · report
gaussian_2d arthur-qiu/freetraj/lvdm/modules/attention_freetraj.py official repository unverified Apache-2.0 (permissive) · 3fa8442a049bccd4 · report
scale_module arthur-qiu/freetraj/lvdm/basics.py official repository unverified Apache-2.0 (permissive) · 9136b5f9b735334b · report

Tasks

Video Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionDiffusionFocusOPTSoftmax

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