GraphVid: Interactive Graph-Controllable Video Generation

Hugging Face Daily Papers Papers
controllable-video-generation graph-conditioned image-to-video interaction-graph video-generation

Summary

GraphVid introduces a graph-conditioned image-to-video generation model that enables interactive control through structured interaction graphs, outperforming prior methods with significant reductions in FID and FVD.

Controllable video generation remains challenging due to the difficulty of specifying precise multi-object interactions using text prompts or motion-control inputs that primarily constrain pixel movement. In practice, trajectory-based control often requires users to draw accurate tracks for multiple objects, which scales poorly with scene complexity and becomes ambiguous under occlusion or overlap. To enable flexible yet precise multi-subject control, we introduce GraphVid, a graph-conditioned image-to-video generation model that enables interactive control through structured interaction graphs. We further curate GraphVid-Bench, a large-scale interaction-centric video dataset with structured relational annotations to enable training of interaction-aware video generation models. Despite using substantially less training data and fewer trainable parameters than prior motion-control methods, GraphVid delivers strong controllability and video quality. Compared with Motion-I2V, GraphVid reduces FID by up to 39.9% and FVD by 37.6%, while improving PSNR (9.87=>15.98) and SSIM (0.38=>0.61). Our results highlight the potential of structured semantic interfaces as a powerful paradigm for controllable video generation.
Original Article
View Cached Full Text

Cached at: 07/24/26, 05:06 AM

Paper page - GraphVid: Interactive Graph-Controllable Video Generation

Source: https://huggingface.co/papers/2607.21580

Abstract

Controllablevideogenerationremainschallengingduetothedifficultyofspecifyingprecisemulti-objectinteractionsusingtextpromptsormotion-controlinputsthatprimarilyconstrainpixelmovement.Inpractice,trajectory-basedcontroloftenrequiresuserstodrawaccuratetracksformultipleobjects,whichscalespoorlywithscenecomplexityandbecomesambiguousunderocclusionoroverlap.Toenableflexibleyetprecisemulti-subjectcontrol,weintroduceGraphVid,agraph-conditionedimage-to-videogenerationmodelthatenablesinteractivecontrolthroughstructuredinteractiongraphs.WefurthercurateGraphVid-Bench,alarge-scaleinteraction-centricvideodatasetwithstructuredrelationalannotationstoenabletrainingofinteraction-awarevideogenerationmodels.Despiteusingsubstantiallylesstrainingdataandfewertrainableparametersthanpriormotion-controlmethods,GraphViddeliversstrongcontrollabilityandvideoquality.ComparedwithMotion-I2V,GraphVidreducesFIDbyupto39.9%andFVDby37.6%,whileimprovingPSNR(9.87=>15.98)andSSIM(0.38=>0.61).Ourresultshighlightthepotentialofstructuredsemanticinterfacesasapowerfulparadigmforcontrollablevideogeneration.

View arXiv pageView PDFProject pageAdd to collection

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.21580 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.21580 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.21580 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Vidu S1: A Real-Time Interactive Video Generation Model

Hugging Face Daily Papers

Vidu S1 is a real-time interactive video generation model that enables voice-controlled digital character animation with infinite-length output and high frame rate on consumer GPUs, achieving state-of-the-art performance.

CogOmniControl: Reasoning-Driven Controllable Video Generation via Creative Intent Cognition

Hugging Face Daily Papers

CogOmniControl is a reasoning-driven framework for controllable video generation that uses a specialized vision-language model (CogVLM) trained on anime production data to infer creative intent from sparse conditions, then guides a diffusion-based generator via reinforcement learning, achieving state-of-the-art results on new benchmarks.

ID-V2V: Identity-Preserving Video Restylization

Hugging Face Daily Papers

ID-V2V is a video-to-video generative framework for identity-preserving video restylization. It treats identity preservation as a video relighting problem and uses edited keyframes for style propagation, achieving high-quality results without paired training data.

Towards Consistent Video Geometry Estimation

Hugging Face Daily Papers

ViGeo is a transformer-based foundation model that recovers dense and consistent 3D geometry from videos using dynamic chunking attention and a completion-based data refinement framework, achieving state-of-the-art performance across multiple tasks.