arXiv:2608.22725v1 Announce Type: new Abstract: Short-drama generation has grown into a large, industrialized pipeline, and as it scales from isolated shots to the episode level, visual continuity ha...
arXiv:2609.37407v1 Announce Type: new Abstract: While recent video foundation models excel at generating high-quality short videos, long-form video generation remains a critical challenge, where a ma...
Weave Forcing is a training‑free framework that enhances interactive long video generation by enabling compositional memory routing. It uses an LLM to split user prompts into character and background slots, then applies masked memory weaving with semantic masks to selectively retrieve relevant historical references. The method also introduces coverage‑adaptive RoPE to adjust temporal offsets based on reference coverage, reducing visual artifacts and improving cross‑shot consistency while preserving visual quality and text alignment.
arXiv:2606. 20799v2 Announce Type: replace-cross Abstract: Generating visually consistent multi-shot videos remains an open challenge.
The paper introduces the Multi-Instruction Multi-Shot Long-Video Editing (MMLVE) task, aiming to edit long videos with multiple instructions while maintaining consistency across shots, decoupling instructions, and preserving spatiotemporal structure. It proposes an agentic editing framework that combines Large Language Models and Vision‑Language Models for shot-level decoupling and precise instruction parsing. A new dataset, MMLVE‑Bench, and three evaluation metrics are created to benchmark this task, and experiments show the proposed MMLVE‑Agent outperforms existing closed‑source state‑of‑the‑art methods by eliminating hallucinations and ensuring seamless transitions.
arXiv:2608.28699v1 Announce Type: new Abstract: Understanding long-form video remains a fundamental challenge for multimodal large language models (MLLMs). Sparse frame sampling fails to capture fine...
arXiv:2608.29621v1 Announce Type: cross Abstract: Long-horizon story-driven video generation requires a production agent to coordinate narrative decomposition, state tracking, shot design, prompt con...
arXiv:2610.00097v1 Announce Type: new Abstract: Recent diffusion and autoregressive models have substantially improved text-to-video generation, yet producing coherent long-form story videos with con...
The paper introduces the Multi-Instruction Multi-Shot Long-Video Editing (MMLVE) task, aiming to enable consistent editing of long videos with multiple instructions. It proposes an agentic editing framework that combines Large Language Models and Vision-Language Models for shot-level decoupling and precise instruction parsing. The authors also present the MMLVE-Bench dataset and evaluation metrics, showing that their MMLVE-Agent outperforms existing state‑of‑the‑art methods by eliminating hallucinations and preserving temporal consistency.
arXiv:2606. 26171v1 Announce Type: cross Abstract: Recent image generation models achieve impressive quality in single-image synthesis, but often fail to maintain consistency across sequential outputs, as required in comics, storyboards, and visual narratives.
Short dramas, with their rapid shot rhythms, dialogue-driven focus shifts, and demanding cinematographic grounding, pose challenges that prompt-level or text-only video generation pipelines struggle to meet. We study plot-to-short-drama generation, where a global plot and local context are transformed into visually grounded multi-shot videos.
ConWriter is a training‑free framework that generates long‑form stories scene by scene, using static requirements, dynamic memory, symbolic state reasoning, and uncertainty‑aware risk signals to enforce consistency. It checks each new scene against required narrative transitions and repairs local errors before they propagate. Evaluations on ConStory‑Bench show that ConWriter matches or outperforms direct generation and a recent baseline, improving narrative consistency across multiple models and story lengths.