ContextMaster: Interactive Multi-Shot Video Creation via Fixed-Budget Sparse Context Routing

Hugging Face Daily Papers Papers
video-generation multi-shot-video sparse-context distillation interactive-creation

Summary

ContextMaster is a unified model for interactive multi-shot video creation that maintains shared history across generation, reference conditioning, and editing while using fixed-budget sparse context routing and two-stage privileged context distillation for efficiency.

Recent video models increasingly support generation, reference conditioning, and editing within a single model, yet typically expose them as separate operations over fixed inputs. Practical creation unfolds across multiple shots, requiring one model to generate from text, follow a reference, or edit source footage while maintaining shared history. We formalize this setting as interactive multi-shot video creation (IMVC) and introduce ContextMaster, a unified model with a role-aware context representation for these operations. An interactive model must retain access to an expanding history without allowing the context read cost at each denoising step to grow. ContextMaster combines reusable clean context states with fixed budget sparse context routing and uses ConstraintSink to keep task constraints visible. To address the dual challenges of sparse context access and inference with few denoising steps, we propose a two-stage privileged context distillation framework, which transfers full context behavior from a dense teacher through consistency distillation and then refines deployment rollouts with distribution matching. Experiments on the three primitive tasks demonstrate improved task fulfillment and consistency across shots over specialized baselines. User studies further validate flexibly composed workflows, while the model reaches 16 FPS on a single GPU.
Original Article
View Cached Full Text

Cached at: 08/07/26, 09:56 AM

Paper page - ContextMaster: Interactive Multi-Shot Video Creation via Fixed-Budget Sparse Context Routing

Source: https://huggingface.co/papers/2608.04956 Published on Aug 5

·

Submitted byhttps://huggingface.co/XuGuo699

xuguoon Aug 7

Authors:

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Recentvideomodelsincreasinglysupportgeneration,referenceconditioning,andeditingwithinasinglemodel,yettypicallyexposethemasseparateoperationsoverfixedinputs.Practicalcreationunfoldsacrossmultipleshots,requiringonemodeltogeneratefromtext,followareference,oreditsourcefootagewhilemaintainingsharedhistory.Weformalizethissettingasinteractivemulti-shotvideocreation(IMVC)andintroduceContextMaster,aunifiedmodelwitharole-awarecontextrepresentationfortheseoperations.Aninteractivemodelmustretainaccesstoanexpandinghistorywithoutallowingthecontextreadcostateachdenoisingsteptogrow.ContextMastercombinesreusablecleancontextstateswithfixedbudgetsparsecontextroutingandusesConstraintSinktokeeptaskconstraintsvisible.Toaddressthedualchallengesofsparsecontextaccessandinferencewithfewdenoisingsteps,weproposeatwo-stageprivilegedcontextdistillationframework,whichtransfersfullcontextbehaviorfromadenseteacherthroughconsistencydistillationandthenrefinesdeploymentrolloutswithdistributionmatching.Experimentsonthethreeprimitivetasksdemonstrateimprovedtaskfulfillmentandconsistencyacrossshotsoverspecializedbaselines.Userstudiesfurthervalidateflexiblycomposedworkflows,whilethemodelreaches16FPSonasingleGPU.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2608\.04956

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/2608.04956 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.04956 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.04956 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