Camera and human motion controls have been extensively studied for video generation, but existing approaches typically address them separately, suffering from limited data with high-quality annotations for both aspects. To overcome this, we present Uni3C, a unified 3D-enhanced framework for precise control of both camera and human motion in video generation. Uni3C includes two key contributions. First, we propose a plug-and-play control module trained with a frozen video generative backbone, PCDController, which utilizes unprojected point clouds from monocular depth to achieve accurate camera control. By leveraging the strong 3D priors of point clouds and the powerful capacities of video foundational models, PCDController shows impressive generalization, performing well regardless of whether the inference backbone is frozen or fine-tuned. This flexibility enables different modules of Uni3C to be trained in specific domains, i.e., either camera control or human motion control, reducing the dependency on jointly annotated data. Second, we propose a jointly aligned 3D world guidance for the inference phase that seamlessly integrates both scenic point clouds and SMPL-X characters to unify the control signals for camera and human motion, respectively. Extensive experiments confirm that PCDController enjoys strong robustness in driving camera motion for fine-tuned backbones of video generation. Uni3C substantially outperforms competitors in both camera controllability and human motion quality. Additionally, we collect tailored validation sets featuring challenging camera movements and human actions to validate the effectiveness of our method.
The evolution of Text-to-video (T2V) generative models, trained on large-scale datasets, has been marked by significant progress. However, the sensitivity of T2V generative models to input prompts highlights the critical role of prompt design in influencing generative outcomes. Prior research has predominantly relied on Large Language Models (LLMs) to align user-provided prompts with the distribution of training prompts, albeit without tailored guidance encompassing prompt vocabulary and sentence structure nuances. To this end, we introduce RAPO, a novel Retrieval-Augmented Prompt Optimization framework. In order to address potential inaccuracies and ambiguous details generated by LLM-generated prompts. RAPO refines the naive prompts through dual optimization branches, selecting the superior prompt for T2V generation. The first branch augments user prompts with diverse modifiers extracted from a learned relational graph, refining them to align with the format of training prompts via a fine-tuned LLM. Conversely, the second branch rewrites the naive prompt using a pre-trained LLM following a well-defined instruction set. Extensive experiments demonstrate that RAPO can effectively enhance both the static and dynamic dimensions of generated videos, demonstrating the significance of prompt optimization for user-provided prompts.
Diffusion Transformer (DiT), an emerging diffusion model for visual generation, has demonstrated superior performance but suffers from substantial computational costs. Our investigations reveal that these costs primarily stem from the \emph{static} inference paradigm, which inevitably introduces redundant computation in certain \emph{diffusion timesteps} and \emph{spatial regions}. To overcome this inefficiency, we propose \textbf{Dy}namic \textbf{Di}ffusion \textbf{T}ransformer (DyDiT), an architecture that \emph{dynamically} adjusts its computation along both \emph{timestep} and \emph{spatial} dimensions. Specifically, we introduce a \emph{Timestep-wise Dynamic Width} (TDW) approach that adapts model width conditioned on the generation timesteps. In addition, we design a \emph{Spatial-wise Dynamic Token} (SDT) strategy to avoid redundant computation at unnecessary spatial locations. TDW and SDT can be seamlessly integrated into DiT and significantly accelerates the generation process. Building on these designs, we further enhance DyDiT in three key aspects. First, DyDiT is integrated seamlessly with flow matching-based generation, enhancing its versatility. Furthermore, we enhance DyDiT to tackle more complex visual generation tasks, including video generation and text-to-image generation, thereby broadening its real-world applications. Finally, to address the high cost of full fine-tuning and democratize technology access, we investigate the feasibility of training DyDiT in a parameter-efficient manner and introduce timestep-based dynamic LoRA (TD-LoRA). Extensive experiments on diverse visual generation models, including DiT, SiT, Latte, and FLUX, demonstrate the effectiveness of DyDiT.
Diffusion Transformer(DiT)-based generation models have achieved remarkable success in video generation. However, their inherent computational demands pose significant efficiency challenges. In this paper, we exploit the inherent temporal non-uniformity of real-world videos and observe that videos exhibit dynamic information density, with high-motion segments demanding greater detail preservation than static scenes. Inspired by this temporal non-uniformity, we propose VGDFR, a training-free approach for Diffusion-based Video Generation with Dynamic Latent Frame Rate. VGDFR adaptively adjusts the number of elements in latent space based on the motion frequency of the latent space content, using fewer tokens for low-frequency segments while preserving detail in high-frequency segments. Specifically, our key contributions are: (1) A dynamic frame rate scheduler for DiT video generation that adaptively assigns frame rates for video segments. (2) A novel latent-space frame merging method to align latent representations with their denoised counterparts before merging those redundant in low-resolution space. (3) A preference analysis of Rotary Positional Embeddings (RoPE) across DiT layers, informing a tailored RoPE strategy optimized for semantic and local information capture. Experiments show that VGDFR can achieve a speedup up to 3x for video generation with minimal quality degradation.
Text-to-Video generation, which utilizes the provided text prompt to generate high-quality videos, has drawn increasing attention and achieved great success due to the development of diffusion models recently. Existing methods mainly rely on a pre-trained text encoder to capture the semantic information and perform cross attention with the encoded text prompt to guide the generation of video. However, when it comes to complex prompts that contain dynamic scenes and multiple camera-view transformations, these methods can not decompose the overall information into separate scenes, as well as fail to smoothly change scenes based on the corresponding camera-views. To solve these problems, we propose a novel method, i.e., Modular-Cam. Specifically, to better understand a given complex prompt, we utilize a large language model to analyze user instructions and decouple them into multiple scenes together with transition actions. To generate a video containing dynamic scenes that match the given camera-views, we incorporate the widely-used temporal transformer into the diffusion model to ensure continuity within a single scene and propose CamOperator, a modular network based module that well controls the camera movements. Moreover, we propose AdaControlNet, which utilizes ControlNet to ensure consistency across scenes and adaptively adjusts the color tone of the generated video. Extensive qualitative and quantitative experiments prove our proposed Modular-Cam's strong capability of generating multi-scene videos together with its ability to achieve fine-grained control of camera movements. Generated results are available at https://modular-cam.github.io.
Recent advances in video generation have been driven by diffusion models and autoregressive frameworks, yet critical challenges persist in harmonizing prompt adherence, visual quality, motion dynamics, and duration: compromises in motion dynamics to enhance temporal visual quality, constrained video duration (5-10 seconds) to prioritize resolution, and inadequate shot-aware generation stemming from general-purpose MLLMs' inability to interpret cinematic grammar, such as shot composition, actor expressions, and camera motions. These intertwined limitations hinder realistic long-form synthesis and professional film-style generation. To address these limitations, we propose SkyReels-V2, an Infinite-length Film Generative Model, that synergizes Multi-modal Large Language Model (MLLM), Multi-stage Pretraining, Reinforcement Learning, and Diffusion Forcing Framework. Firstly, we design a comprehensive structural representation of video that combines the general descriptions by the Multi-modal LLM and the detailed shot language by sub-expert models. Aided with human annotation, we then train a unified Video Captioner, named SkyCaptioner-V1, to efficiently label the video data. Secondly, we establish progressive-resolution pretraining for the fundamental video generation, followed by a four-stage post-training enhancement: Initial concept-balanced Supervised Fine-Tuning (SFT) improves baseline quality; Motion-specific Reinforcement Learning (RL) training with human-annotated and synthetic distortion data addresses dynamic artifacts; Our diffusion forcing framework with non-decreasing noise schedules enables long-video synthesis in an efficient search space; Final high-quality SFT refines visual fidelity. All the code and models are available at https://github.com/SkyworkAI/SkyReels-V2.
We introduce CamMimic, an innovative algorithm tailored for dynamic video editing needs. It is designed to seamlessly transfer the camera motion observed in a given reference video onto any scene of the user's choice in a zero-shot manner without requiring any additional data. Our algorithm achieves this using a two-phase strategy by leveraging a text-to-video diffusion model. In the first phase, we develop a multi-concept learning method using a combination of LoRA layers and an orthogonality loss to capture and understand the underlying spatial-temporal characteristics of the reference video as well as the spatial features of the user's desired scene. The second phase proposes a unique homography-based refinement strategy to enhance the temporal and spatial alignment of the generated video. We demonstrate the efficacy of our method through experiments conducted on a dataset containing combinations of diverse scenes and reference videos containing a variety of camera motions. In the absence of an established metric for assessing camera motion transfer between unrelated scenes, we propose CameraScore, a novel metric that utilizes homography representations to measure camera motion similarity between the reference and generated videos. Extensive quantitative and qualitative evaluations demonstrate that our approach generates high-quality, motion-enhanced videos. Additionally, a user study reveals that 70.31% of participants preferred our method for scene preservation, while 90.45% favored it for motion transfer. We hope this work lays the foundation for future advancements in camera motion transfer across different scenes.
Recent advances in video generation have posed great challenges in the assessment of AI-generated content, particularly with the emergence of increasingly sophisticated models. The various inconsistencies and defects observed in such videos are inherently complex, making overall scoring notoriously difficult. In this paper, we emphasize the critical importance of integrating fine-grained reasoning into video evaluation, and we propose $\textbf{F}$ing$\textbf{ER}$, a novel entity-level reasoning evaluation framework that first automatically generates $\textbf{F}$ine-grained $\textbf{E}$ntity-level questions, and then answers those questions by a $\textbf{R}$easoning model with scores, which can be subsequently weighted summed to an overall score for different applications. Specifically, we leverage LLMs to derive entity-level questions across five distinct perspectives, which (i) often focus on some specific entities of the content, thereby making answering or scoring much easier by MLLMs, and (ii) are more interpretable. Then we construct a FingER dataset, consisting of approximately 3.3k videos and corresponding 60k fine-grained QA annotations, each with detailed reasons. Based on that, we further investigate various training protocols to best incentivize the reasoning capability of MLLMs for correct answer prediction. Extensive experiments demonstrate that a reasoning model trained using Group Relative Policy Optimization (GRPO) with a cold-start strategy achieves the best performance. Notably, our model surpasses existing methods by a relative margin of $11.8\%$ on GenAI-Bench and $5.5\%$ on MonetBench with only 3.3k training videos, which is at most one-tenth of the training samples utilized by other methods. Our code and dataset will be released soon.
In this paper, we propose a novel framework for controllable video diffusion, OmniVDiff, aiming to synthesize and comprehend multiple video visual content in a single diffusion model. To achieve this, OmniVDiff treats all video visual modalities in the color space to learn a joint distribution, while employing an adaptive control strategy that dynamically adjusts the role of each visual modality during the diffusion process, either as a generation modality or a conditioning modality. This allows flexible manipulation of each modality's role, enabling support for a wide range of tasks. Consequently, our model supports three key functionalities: (1) Text-conditioned video generation: multi-modal visual video sequences (i.e., rgb, depth, canny, segmentaion) are generated based on the text conditions in one diffusion process; (2) Video understanding: OmniVDiff can estimate the depth, canny map, and semantic segmentation across the input rgb frames while ensuring coherence with the rgb input; and (3) X-conditioned video generation: OmniVDiff generates videos conditioned on fine-grained attributes (e.g., depth maps or segmentation maps). By integrating these diverse tasks into a unified video diffusion framework, OmniVDiff enhances the flexibility and scalability for controllable video diffusion, making it an effective tool for a variety of downstream applications, such as video-to-video translation. Extensive experiments demonstrate the effectiveness of our approach, highlighting its potential for various video-related applications.
In this paper, we propose H-MoRe, a novel pipeline for learning precise human-centric motion representation. Our approach dynamically preserves relevant human motion while filtering out background movement. Notably, unlike previous methods relying on fully supervised learning from synthetic data, H-MoRe learns directly from real-world scenarios in a self-supervised manner, incorporating both human pose and body shape information. Inspired by kinematics, H-MoRe represents absolute and relative movements of each body point in a matrix format that captures nuanced motion details, termed world-local flows. H-MoRe offers refined insights into human motion, which can be integrated seamlessly into various action-related applications. Experimental results demonstrate that H-MoRe brings substantial improvements across various downstream tasks, including gait recognition(CL@R1: +16.01%), action recognition(Acc@1: +8.92%), and video generation(FVD: -67.07%). Additionally, H-MoRe exhibits high inference efficiency (34 fps), making it suitable for most real-time scenarios. Models and code will be released upon publication.
Autoencoder (AE) is the key to the success of latent diffusion models for image and video generation, reducing the denoising resolution and improving efficiency. However, the power of AE has long been underexplored in terms of network design, compression ratio, and training strategy. In this work, we systematically examine the architecture design choices and optimize the computation distribution to obtain a series of efficient and high-compression video AEs that can decode in real time on mobile devices. We also unify the design of plain Autoencoder and image-conditioned I2V VAE, achieving multifunctionality in a single network. In addition, we find that the widely adopted discriminative losses, i.e., GAN, LPIPS, and DWT losses, provide no significant improvements when training AEs at scale. We propose a novel latent consistency loss that does not require complicated discriminator design or hyperparameter tuning, but provides stable improvements in reconstruction quality. Our AE achieves an ultra-high compression ratio and real-time decoding speed on mobile while outperforming prior art in terms of reconstruction metrics by a large margin. We finally validate our AE by training a DiT on its latent space and demonstrate fast, high-quality text-to-video generation capability.
High resolution panoramic video content is paramount for immersive experiences in Virtual Reality, but is non-trivial to collect as it requires specialized equipment and intricate camera setups. In this work, we introduce VideoPanda, a novel approach for synthesizing 360$^\circ$ videos conditioned on text or single-view video data. VideoPanda leverages multi-view attention layers to augment a video diffusion model, enabling it to generate consistent multi-view videos that can be combined into immersive panoramic content. VideoPanda is trained jointly using two conditions: text-only and single-view video, and supports autoregressive generation of long-videos. To overcome the computational burden of multi-view video generation, we randomly subsample the duration and camera views used during training and show that the model is able to gracefully generalize to generating more frames during inference. Extensive evaluations on both real-world and synthetic video datasets demonstrate that VideoPanda generates more realistic and coherent 360$^\circ$ panoramas across all input conditions compared to existing methods. Visit the project website at https://research.nvidia.com/labs/toronto-ai/VideoPanda/ for results.
Recent video generation research has focused heavily on isolated actions, leaving interactive motions-such as hand-face interactions-largely unexamined. These interactions are essential for emerging biometric authentication systems, which rely on interactive motion-based anti-spoofing approaches. From a security perspective, there is a growing need for large-scale, high-quality interactive videos to train and strengthen authentication models. In this work, we introduce a novel paradigm for animating realistic hand-face interactions. Our approach simultaneously learns spatio-temporal contact dynamics and biomechanically plausible deformation effects, enabling natural interactions where hand movements induce anatomically accurate facial deformations while maintaining collision-free contact. To facilitate this research, we present InterHF, a large-scale hand-face interaction dataset featuring 18 interaction patterns and 90,000 annotated videos. Additionally, we propose InterAnimate, a region-aware diffusion model designed specifically for interaction animation. InterAnimate leverages learnable spatial and temporal latents to effectively capture dynamic interaction priors and integrates a region-aware interaction mechanism that injects these priors into the denoising process. To the best of our knowledge, this work represents the first large-scale effort to systematically study human hand-face interactions. Qualitative and quantitative results show InterAnimate produces highly realistic animations, setting a new benchmark. Code and data will be made public to advance research.
Audio-driven cospeech video generation typically involves two stages: speech-to-gesture and gesture-to-video. While significant advances have been made in speech-to-gesture generation, synthesizing natural expressions and gestures remains challenging in gesture-to-video systems. In order to improve the generation effect, previous works adopted complex input and training strategies and required a large amount of data sets for pre-training, which brought inconvenience to practical applications. We propose a simple one-stage training method and a temporal inference method based on a diffusion model to synthesize realistic and continuous gesture videos without the need for additional training of temporal modules.The entire model makes use of existing pre-trained weights, and only a few thousand frames of data are needed for each character at a time to complete fine-tuning. Built upon the video generator, we introduce a new audio-to-video pipeline to synthesize co-speech videos, using 2D human skeleton as the intermediate motion representation. Our experiments show that our method outperforms existing GAN-based and diffusion-based methods.
Recent advances in camera-controllable video generation have been constrained by the reliance on static-scene datasets with relative-scale camera annotations, such as RealEstate10K. While these datasets enable basic viewpoint control, they fail to capture dynamic scene interactions and lack metric-scale geometric consistency-critical for synthesizing realistic object motions and precise camera trajectories in complex environments. To bridge this gap, we introduce the first fully open-source, high-resolution dynamic-scene dataset with metric-scale camera annotations in https://github.com/ZGCTroy/RealCam-Vid.
This technical report presents a cost-efficient strategy for training a video generation foundation model. We present a mid-sized research model with approximately 7 billion parameters (7B) called Seaweed-7B trained from scratch using 665,000 H100 GPU hours. Despite being trained with moderate computational resources, Seaweed-7B demonstrates highly competitive performance compared to contemporary video generation models of much larger size. Design choices are especially crucial in a resource-constrained setting. This technical report highlights the key design decisions that enhance the performance of the medium-sized diffusion model. Empirically, we make two observations: (1) Seaweed-7B achieves performance comparable to, or even surpasses, larger models trained on substantially greater GPU resources, and (2) our model, which exhibits strong generalization ability, can be effectively adapted across a wide range of downstream applications either by lightweight fine-tuning or continue training. See the project page at https://seaweed.video/
Recent advancements in text-to-video (T2V) diffusion models have significantly enhanced the visual quality of the generated videos. However, even recent T2V models find it challenging to follow text descriptions accurately, especially when the prompt requires accurate control of spatial layouts or object trajectories. A recent line of research uses layout guidance for T2V models that require fine-tuning or iterative manipulation of the attention map during inference time. This significantly increases the memory requirement, making it difficult to adopt a large T2V model as a backbone. To address this, we introduce Video-MSG, a training-free Guidance method for T2V generation based on Multimodal planning and Structured noise initialization. Video-MSG consists of three steps, where in the first two steps, Video-MSG creates Video Sketch, a fine-grained spatio-temporal plan for the final video, specifying background, foreground, and object trajectories, in the form of draft video frames. In the last step, Video-MSG guides a downstream T2V diffusion model with Video Sketch through noise inversion and denoising. Notably, Video-MSG does not need fine-tuning or attention manipulation with additional memory during inference time, making it easier to adopt large T2V models. Video-MSG demonstrates its effectiveness in enhancing text alignment with multiple T2V backbones (VideoCrafter2 and CogVideoX-5B) on popular T2V generation benchmarks (T2VCompBench and VBench). We provide comprehensive ablation studies about noise inversion ratio, different background generators, background object detection, and foreground object segmentation.
Human-centric motion control in video generation remains a critical challenge, particularly when jointly controlling camera movements and human poses in scenarios like the iconic Grammy Glambot moment. While recent video diffusion models have made significant progress, existing approaches struggle with limited motion representations and inadequate integration of camera and human motion controls. In this work, we present TokenMotion, the first DiT-based video diffusion framework that enables fine-grained control over camera motion, human motion, and their joint interaction. We represent camera trajectories and human poses as spatio-temporal tokens to enable local control granularity. Our approach introduces a unified modeling framework utilizing a decouple-and-fuse strategy, bridged by a human-aware dynamic mask that effectively handles the spatially-and-temporally varying nature of combined motion signals. Through extensive experiments, we demonstrate TokenMotion's effectiveness across both text-to-video and image-to-video paradigms, consistently outperforming current state-of-the-art methods in human-centric motion control tasks. Our work represents a significant advancement in controllable video generation, with particular relevance for creative production applications.
Diffusion generative models have demonstrated remarkable success in visual domains such as image and video generation. They have also recently emerged as a promising approach in robotics, especially in robot manipulations. Diffusion models leverage a probabilistic framework, and they stand out with their ability to model multi-modal distributions and their robustness to high-dimensional input and output spaces. This survey provides a comprehensive review of state-of-the-art diffusion models in robotic manipulation, including grasp learning, trajectory planning, and data augmentation. Diffusion models for scene and image augmentation lie at the intersection of robotics and computer vision for vision-based tasks to enhance generalizability and data scarcity. This paper also presents the two main frameworks of diffusion models and their integration with imitation learning and reinforcement learning. In addition, it discusses the common architectures and benchmarks and points out the challenges and advantages of current state-of-the-art diffusion-based methods.
Recently, image-to-video (I2V) diffusion models have demonstrated impressive scene understanding and generative quality, incorporating image conditions to guide generation. However, these models primarily animate static images without extending beyond their provided context. Introducing additional constraints, such as camera trajectories, can enhance diversity but often degrades visual quality, limiting their applicability for tasks requiring faithful scene representation. We propose CamContextI2V, an I2V model that integrates multiple image conditions with 3D constraints alongside camera control to enrich both global semantics and fine-grained visual details. This enables more coherent and context-aware video generation. Moreover, we motivate the necessity of temporal awareness for an effective context representation. Our comprehensive study on the RealEstate10K dataset demonstrates improvements in visual quality and camera controllability. We make our code and models publicly available at: https://github.com/LDenninger/CamContextI2V.