ShotPlan: Cinematic Video Generation with Learnable Planning Token

Hugging Face Daily Papers Papers

Summary

ShotPlan introduces learnable planning tokens with fractional temporal rotary position embeddings for cinematic multi-shot video generation, enabling explicit shot-level planning and achieving superior inter-shot consistency.

Current video generation models achieve impressive results in single-shot generation, yet remain limited in cinematic video generation, where coherent narratives and effective multi-shot composition require explicit shot planning. To address this challenge, we propose ShotPlan, a framework for explicit multi-shot cinematic video generation built upon a video diffusion foundation model. Our method introduces learnable planning tokens that capture shot-level transition cues and can be seamlessly integrated with the original video generation tokens to control transition timestamps. Unlike standard video generation tokens, the proposed planning tokens are equipped with Fractional Temporal Rotary Position Embedding (FRoPE), enabling shot transitions to be modeled at the frame level. Experiments demonstrate that ShotPlan significantly outperforms existing cinematic video generation methods, offering more flexible shot management and stronger inter-shot consistency.
Original Article
View Cached Full Text

Cached at: 07/21/26, 02:37 PM

Paper page - ShotPlan: Cinematic Video Generation with Learnable Planning Token

Source: https://huggingface.co/papers/2607.17675 Published on Jul 20

·

Submitted byhttps://huggingface.co/Pensioner

suguoon Jul 21

Abstract

Currentvideogenerationmodelsachieveimpressiveresultsinsingle-shotgeneration,yetremainlimitedincinematicvideogeneration,wherecoherentnarrativesandeffectivemulti-shotcompositionrequireexplicitshotplanning.Toaddressthischallenge,weproposeShotPlan,aframeworkforexplicitmulti-shotcinematicvideogenerationbuiltuponavideodiffusionfoundationmodel.Ourmethodintroduceslearnableplanningtokensthatcaptureshot-leveltransitioncuesandcanbeseamlesslyintegratedwiththeoriginalvideogenerationtokenstocontroltransitiontimestamps.Unlikestandardvideogenerationtokens,theproposedplanningtokensareequippedwithFractionalTemporalRotaryPositionEmbedding(FRoPE),enablingshottransitionstobemodeledattheframelevel.ExperimentsdemonstratethatShotPlansignificantlyoutperformsexistingcinematicvideogenerationmethods,offeringmoreflexibleshotmanagementandstrongerinter-shotconsistency.

View arXiv pageView PDFProject pageGitHub5Add to collection

Get this paper in your agent:

hf papers read 2607\.17675

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.17675 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.17675 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.17675 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

UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating

Hugging Face Daily Papers

UnityShots is a memory-driven multi-shot audio-video generation system that maintains consistent subject appearance and audio across video cuts using fixed-size long-term and short-term memory slots with boundary-conditioned gates and discrete cut-type priors. It outperforms open-source baselines on cross-shot coherence metrics and matches closed-source systems.