REVIEW 12 cited by
StoryAgent: Customized Storytelling Video Generation via Multi-Agent Collaboration
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
The advent of AI-Generated Content (AIGC) has spurred research into automated video generation to streamline conventional processes. However, automating storytelling video production, particularly for customized narratives, remains challenging due to the complexity of maintaining subject consistency across shots. While existing approaches like Mora and AesopAgent integrate multiple agents for Story-to-Video (S2V) generation, they fall short in preserving protagonist consistency and supporting Customized Storytelling Video Generation (CSVG). To address these limitations, we propose StoryAgent, a multi-agent framework designed for CSVG. StoryAgent decomposes CSVG into distinct subtasks assigned to specialized agents, mirroring the professional production process. Notably, our framework includes agents for story design, storyboard generation, video creation, agent coordination, and result evaluation. Leveraging the strengths of different models, StoryAgent enhances control over the generation process, significantly improving character consistency. Specifically, we introduce a customized Image-to-Video (I2V) method, LoRA-BE, to enhance intra-shot temporal consistency, while a novel storyboard generation pipeline is proposed to maintain subject consistency across shots. Extensive experiments demonstrate the effectiveness of our approach in synthesizing highly consistent storytelling videos, outperforming state-of-the-art methods. Our contributions include the introduction of StoryAgent, a versatile framework for video generation tasks, and novel techniques for preserving protagonist consistency.
Forward citations
Cited by 12 Pith papers
-
FilmWorld: Agentic Novel-to-Film Generation through Dynamic Cinematic World Modeling
FilmWorld generates multi-scene films from novels by materializing an explicit evolving world-state trajectory and rendering shots in parallel, beating five agents on its own FilmEval benchmark.
-
Autoregressive Modeling of Film with Applications in Video Montage
An autoregressive transformer with an explicit cut token and footage-constrained decoding edits raw video into sequences that people rate as better than two prior automated editing methods.
-
GroundShot: Visually Consistent Multi-Shot Long Video Generation via Entity-Grounded Shot Scheduling
GroundShot introduces entity-grounded shot scheduling with online visual memory to improve consistency in multi-shot video generation and presents GroundBench for entity-level evaluation.
-
Authoring for Living Worlds: Tool-Constrained LLM Agents for Executable Multi-Actor Scenarios
Tool-validated LLM agents author formal event-graph story specifications that a deterministic game engine executes into multi-actor videos with perfect annotations, reaching 80% seeded end-to-end success versus 0% for...
-
AgentHOI: Multi-Agent Reasoning for Human-Object-Interaction Video Generation via Implicit Representation Alignment
AgentHOI generates human-object interaction videos from text plus one human image and one object image, using multi-agent action planning and implicit text-to-motion feature alignment inside a video diffusion model.
-
When Cultures Move: Measuring and Improving Multicultural Text-to-Video Generation
Parallel, role-specialized prompt agents improve cultural relevance in text-to-video generation, with a new cross-cultural benchmark showing the largest gains for location cues.
-
MAR3: Multi-Agent Recognition, Reasoning, and Reflection for Reference Audio-Visual Segmentation
A training-free multi-agent system (Delphi recognition, modality-adaptive reasoning, reflective mask correction) reaches 69.2% J&F on Ref-AVSBench, +3.4 over prior SOTA.
-
OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation
OmniHuman-1.5 combines MLLM-based planning with a multimodal diffusion transformer and pseudo-last-frame identity conditioning to generate context-aware avatar videos from audio and a reference image.
-
Audit & Repair: An Agentic Framework for Consistent Story Visualization in Text-to-Image Diffusion Models
A multi-agent system that audits story images with a vision-language model and repairs inconsistencies with targeted diffusion edits improves multi-panel consistency over existing story visualization methods.
-
BridgeIV: Bridging Customized Image and Video Generation through Test-Time Autoregressive Identity Propagation
BridgeIV improves subject consistency in customized text-to-video generation by warping attention maps and self-attention values across frames, then refining latents with a CLIP-based reward.
-
Infinite Worlds with Versatile Interactions
An open-source causal video world model sustains hour-long, 720p/60fps interactive generation without visual drift, paired with a VLM-based director-pilot agentic harness for rich, open-ended interaction.
-
ViMax: Agentic Video Generation
ViMax introduces a hierarchical multi-agent framework for long-form video generation that uses retrieval-augmented narrative planning and dependency-aware visual state tracking to maintain coherence across scenes.
Discussion (0). Continue with ORCID to comment.