In this paper, we introduce ManiVideo, a novel method for generating consistent and temporally coherent bimanual hand-object manipulation videos from given motion sequences of hands and objects. The core idea of ManiVideo is the construction of a multi-layer occlusion (MLO) representation that learns 3D occlusion relationships from occlusion-free normal maps and occlusion confidence maps. By embedding the MLO structure into the UNet in two forms, the model enhances the 3D consistency of dexterous hand-object manipulation. To further achieve the generalizable grasping of objects, we integrate Objaverse, a large-scale 3D object dataset, to address the scarcity of video data, thereby facilitating the learning of extensive object consistency. Additionally, we propose an innovative training strategy that effectively integrates multiple datasets, supporting downstream tasks such as human-centric hand-object manipulation video generation. Through extensive experiments, we demonstrate that our approach not only achieves video generation with plausible hand-object interaction and generalizable objects, but also outperforms existing SOTA methods.
The current state-of-the-art video generative models can produce commercial-grade videos with highly realistic details. However, they still struggle to coherently present multiple sequential events in the stories specified by the prompts, which is foreseeable an essential capability for future long video generation scenarios. For example, top T2V generative models still fail to generate a video of the short simple story 'how to put an elephant into a refrigerator.' While existing detail-oriented benchmarks primarily focus on fine-grained metrics like aesthetic quality and spatial-temporal consistency, they fall short of evaluating models' abilities to handle event-level story presentation. To address this gap, we introduce StoryEval, a story-oriented benchmark specifically designed to assess text-to-video (T2V) models' story-completion capabilities. StoryEval features 423 prompts spanning 7 classes, each representing short stories composed of 2-4 consecutive events. We employ advanced vision-language models, such as GPT-4V and LLaVA-OV-Chat-72B, to verify the completion of each event in the generated videos, applying a unanimous voting method to enhance reliability. Our methods ensure high alignment with human evaluations, and the evaluation of 11 models reveals its challenge, with none exceeding an average story-completion rate of 50%. StoryEval provides a new benchmark for advancing T2V models and highlights the challenges and opportunities in developing next-generation solutions for coherent story-driven video generation.
Diffusion models have achieved remarkable success in the image and video generation tasks. Nevertheless, they often require a large amount of memory and time overhead during inference, due to the complex network architecture and considerable number of timesteps for iterative diffusion. Recently, the post-training quantization (PTQ) technique has proved a promising way to reduce the inference cost by quantizing the float-point operations to low-bit ones. However, most of them fail to tackle with the large variations in the distribution of activations across distinct channels and timesteps, as well as the inconsistent of input between quantization and inference on diffusion models, thus leaving much room for improvement. To address the above issues, we propose a novel method dubbed Timestep-Channel Adaptive Quantization for Diffusion Models (TCAQ-DM). Specifically, we develop a timestep-channel joint reparameterization (TCR) module to balance the activation range along both the timesteps and channels, facilitating the successive reconstruction procedure. Subsequently, we employ a dynamically adaptive quantization (DAQ) module that mitigate the quantization error by selecting an optimal quantizer for each post-Softmax layers according to their specific types of distributions. Moreover, we present a progressively aligned reconstruction (PAR) strategy to mitigate the bias caused by the input mismatch. Extensive experiments on various benchmarks and distinct diffusion models demonstrate that the proposed method substantially outperforms the state-of-the-art approaches in most cases, especially yielding comparable FID metrics to the full precision model on CIFAR-10 in the W6A6 setting, while enabling generating available images in the W4A4 settings.
Generating high-quality videos from textual descriptions poses challenges in maintaining temporal coherence and control over subject motion. We propose VAST (Video As Storyboard from Text), a two-stage framework to address these challenges and enable high-quality video generation. In the first stage, StoryForge transforms textual descriptions into detailed storyboards, capturing human poses and object layouts to represent the structural essence of the scene. In the second stage, VisionForge generates videos from these storyboards, producing high-quality videos with smooth motion, temporal consistency, and spatial coherence. By decoupling text understanding from video generation, VAST enables precise control over subject dynamics and scene composition. Experiments on the VBench benchmark demonstrate that VAST outperforms existing methods in both visual quality and semantic expression, setting a new standard for dynamic and coherent video generation.
Text-editable and pose-controllable character video generation is a challenging but prevailing topic with practical applications. However, existing approaches mainly focus on single-object video generation with pose guidance, ignoring the realistic situation that multi-character appear concurrently in a scenario. To tackle this, we propose a novel multi-character video generation framework in a tuning-free manner, which is based on the separated text and pose guidance. Specifically, we first extract character masks from the pose sequence to identify the spatial position for each generating character, and then single prompts for each character are obtained with LLMs for precise text guidance. Moreover, the spatial-aligned cross attention and multi-branch control module are proposed to generate fine grained controllable multi-character video. The visualized results of generating video demonstrate the precise controllability of our method for multi-character generation. We also verify the generality of our method by applying it to various personalized T2I models. Moreover, the quantitative results show that our approach achieves superior performance compared with previous works.
Learning a robust video Variational Autoencoder (VAE) is essential for reducing video redundancy and facilitating efficient video generation. Directly applying image VAEs to individual frames in isolation can result in temporal inconsistencies and suboptimal compression rates due to a lack of temporal compression. Existing Video VAEs have begun to address temporal compression; however, they often suffer from inadequate reconstruction performance. In this paper, we present a novel and powerful video autoencoder capable of high-fidelity video encoding. First, we observe that entangling spatial and temporal compression by merely extending the image VAE to a 3D VAE can introduce motion blur and detail distortion artifacts. Thus, we propose temporal-aware spatial compression to better encode and decode the spatial information. Additionally, we integrate a lightweight motion compression model for further temporal compression. Second, we propose to leverage the textual information inherent in text-to-video datasets and incorporate text guidance into our model. This significantly enhances reconstruction quality, particularly in terms of detail preservation and temporal stability. Third, we further improve the versatility of our model through joint training on both images and videos, which not only enhances reconstruction quality but also enables the model to perform both image and video autoencoding. Extensive evaluations against strong recent baselines demonstrate the superior performance of our method. The project website can be found at~\href{https://yzxing87.github.io/vae/}{https://yzxing87.github.io/vae/}.
With the development of video generation models has advanced significantly in recent years, we adopt large-scale image-to-video diffusion models for video frame interpolation. We present a conditional encoder designed to adapt an image-to-video model for large-motion frame interpolation. To enhance performance, we integrate a dual-branch feature extractor and propose a cross-frame attention mechanism that effectively captures both spatial and temporal information, enabling accurate interpolations of intermediate frames. Our approach demonstrates superior performance on the Fr\'echet Video Distance (FVD) metric when evaluated against other state-of-the-art approaches, particularly in handling large motion scenarios, highlighting advancements in generative-based methodologies.
Fundus fluorescein angiography (FFA) is critical for diagnosing retinal vascular diseases, but beginners often struggle with image interpretation. This study develops FFA Sora, a text-to-video model that converts FFA reports into dynamic videos via a Wavelet-Flow Variational Autoencoder (WF-VAE) and a diffusion transformer (DiT). Trained on an anonymized dataset, FFA Sora accurately simulates disease features from the input text, as confirmed by objective metrics: Frechet Video Distance (FVD) = 329.78, Learned Perceptual Image Patch Similarity (LPIPS) = 0.48, and Visual-question-answering Score (VQAScore) = 0.61. Specific evaluations showed acceptable alignment between the generated videos and textual prompts, with BERTScore of 0.35. Additionally, the model demonstrated strong privacy-preserving performance in retrieval evaluations, achieving an average Recall@K of 0.073. Human assessments indicated satisfactory visual quality, with an average score of 1.570(scale: 1 = best, 5 = worst). This model addresses privacy concerns associated with sharing large-scale FFA data and enhances medical education.
Despite the considerable progress achieved in the long video generation problem, there is still significant room to improve the consistency of the videos, particularly in terms of smoothness and transitions between scenes. We address these issues to enhance the consistency and coherence of videos generated with either single or multiple prompts. We propose the Time-frequency based temporal Attention Reweighting Algorithm (TiARA), which meticulously edits the attention score matrix based on the Discrete Short-Time Fourier Transform. Our method is supported by a theoretical guarantee, the first-of-its-kind for frequency-based methods in diffusion models. For videos generated by multiple prompts, we further investigate key factors affecting prompt interpolation quality and propose PromptBlend, an advanced prompt interpolation pipeline. The efficacy of our proposed method is validated via extensive experimental results, exhibiting consistent and impressive improvements over baseline methods. The code will be released upon acceptance.
The reliability of substation equipment is crucial to the stability of power systems, but traditional fault analysis methods heavily rely on manual expertise, limiting their effectiveness in handling complex and large-scale data. This paper proposes a substation equipment fault analysis method based on a multimodal large language model (MLLM). We developed a database containing 40,000 entries, including images, defect labels, and analysis reports, and used an image-to-video generation model for data augmentation. Detailed fault analysis reports were generated using GPT-4. Based on this database, we developed SubstationAI, the first model dedicated to substation fault analysis, and designed a fault diagnosis knowledge base along with knowledge enhancement methods. Experimental results show that SubstationAI significantly outperforms existing models, such as GPT-4, across various evaluation metrics, demonstrating higher accuracy and practicality in fault cause analysis, repair suggestions, and preventive measures, providing a more advanced solution for substation equipment fault analysis.
Recent advancements in video autoencoders (Video AEs) have significantly improved the quality and efficiency of video generation. In this paper, we propose a novel and compact video autoencoder, VidTwin, that decouples video into two distinct latent spaces: Structure latent vectors, which capture overall content and global movement, and Dynamics latent vectors, which represent fine-grained details and rapid movements. Specifically, our approach leverages an Encoder-Decoder backbone, augmented with two submodules for extracting these latent spaces, respectively. The first submodule employs a Q-Former to extract low-frequency motion trends, followed by downsampling blocks to remove redundant content details. The second averages the latent vectors along the spatial dimension to capture rapid motion. Extensive experiments show that VidTwin achieves a high compression rate of 0.20% with high reconstruction quality (PSNR of 28.14 on the MCL-JCV dataset), and performs efficiently and effectively in downstream generative tasks. Moreover, our model demonstrates explainability and scalability, paving the way for future research in video latent representation and generation. Check our project page for more details: https://vidtwin.github.io/.
Diffusion probabilistic models have shown significant progress in video generation; however, their computational efficiency is limited by the large number of sampling steps required. Reducing sampling steps often compromises video quality or generation diversity. In this work, we introduce a distillation method that combines variational score distillation and consistency distillation to achieve few-step video generation, maintaining both high quality and diversity. We also propose a latent reward model fine-tuning approach to further enhance video generation performance according to any specified reward metric. This approach reduces memory usage and does not require the reward to be differentiable. Our method demonstrates state-of-the-art performance in few-step generation for 10-second videos (128 frames at 12 FPS). The distilled student model achieves a score of 82.57 on VBench, surpassing the teacher model as well as baseline models Gen-3, T2V-Turbo, and Kling. One-step distillation accelerates the teacher model's diffusion sampling by up to 278.6 times, enabling near real-time generation. Human evaluations further validate the superior performance of our 4-step student models compared to teacher model using 50-step DDIM sampling.
Benefiting from large-scale pre-training of text-video pairs, current text-to-video (T2V) diffusion models can generate high-quality videos from the text description. Besides, given some reference images or videos, the parameter-efficient fine-tuning method, i.e. LoRA, can generate high-quality customized concepts, e.g., the specific subject or the motions from a reference video. However, combining the trained multiple concepts from different references into a single network shows obvious artifacts. To this end, we propose CustomTTT, where we can joint custom the appearance and the motion of the given video easily. In detail, we first analyze the prompt influence in the current video diffusion model and find the LoRAs are only needed for the specific layers for appearance and motion customization. Besides, since each LoRA is trained individually, we propose a novel test-time training technique to update parameters after combination utilizing the trained customized models. We conduct detailed experiments to verify the effectiveness of the proposed methods. Our method outperforms several state-of-the-art works in both qualitative and quantitative evaluations.
Visual representations play a crucial role in developing generalist robotic policies. Previous vision encoders, typically pre-trained with single-image reconstruction or two-image contrastive learning, tend to capture static information, often neglecting the dynamic aspects vital for embodied tasks. Recently, video diffusion models (VDMs) demonstrate the ability to predict future frames and showcase a strong understanding of physical world. We hypothesize that VDMs inherently produce visual representations that encompass both current static information and predicted future dynamics, thereby providing valuable guidance for robot action learning. Based on this hypothesis, we propose the Video Prediction Policy (VPP), which learns implicit inverse dynamics model conditioned on predicted future representations inside VDMs. To predict more precise future, we fine-tune pre-trained video foundation model on robot datasets along with internet human manipulation data. In experiments, VPP achieves a 18.6\% relative improvement on the Calvin ABC-D generalization benchmark compared to the previous state-of-the-art, and demonstrates a 31.6\% increase in success rates for complex real-world dexterous manipulation tasks. Project page at https://video-prediction-policy.github.io
Consistent human-centric image and video synthesis aims to generate images or videos with new poses while preserving appearance consistency with a given reference image, which is crucial for low-cost visual content creation. Recent advances based on diffusion models typically rely on separate networks for reference appearance feature extraction and target visual generation, leading to inconsistent domain gaps between references and targets. In this paper, we frame the task as a spatially-conditioned inpainting problem, where the target image is inpainted to maintain appearance consistency with the reference. This approach enables the reference features to guide the generation of pose-compliant targets within a unified denoising network, thereby mitigating domain gaps. Additionally, to better maintain the reference appearance information, we impose a causal feature interaction framework, in which reference features can only query from themselves, while target features can query appearance information from both the reference and the target. To further enhance computational efficiency and flexibility, in practical implementation, we decompose the spatially-conditioned generation process into two stages: reference appearance extraction and conditioned target generation. Both stages share a single denoising network, with interactions restricted to self-attention layers. This proposed method ensures flexible control over the appearance of generated human images and videos. By fine-tuning existing base diffusion models on human video data, our method demonstrates strong generalization to unseen human identities and poses without requiring additional per-instance fine-tuning. Experimental results validate the effectiveness of our approach, showing competitive performance compared to existing methods for consistent human image and video synthesis.
In this paper, we introduce DirectorLLM, a novel video generation model that employs a large language model (LLM) to orchestrate human poses within videos. As foundational text-to-video models rapidly evolve, the demand for high-quality human motion and interaction grows. To address this need and enhance the authenticity of human motions, we extend the LLM from a text generator to a video director and human motion simulator. Utilizing open-source resources from Llama 3, we train the DirectorLLM to generate detailed instructional signals, such as human poses, to guide video generation. This approach offloads the simulation of human motion from the video generator to the LLM, effectively creating informative outlines for human-centric scenes. These signals are used as conditions by the video renderer, facilitating more realistic and prompt-following video generation. As an independent LLM module, it can be applied to different video renderers, including UNet and DiT, with minimal effort. Experiments on automatic evaluation benchmarks and human evaluations show that our model outperforms existing ones in generating videos with higher human motion fidelity, improved prompt faithfulness, and enhanced rendered subject naturalness.
We propose AV-Link, a unified framework for Video-to-Audio (A2V) and Audio-to-Video (A2V) generation that leverages the activations of frozen video and audio diffusion models for temporally-aligned cross-modal conditioning. The key to our framework is a Fusion Block that facilitates bidirectional information exchange between video and audio diffusion models through temporally-aligned self attention operations. Unlike prior work that uses dedicated models for A2V and V2A tasks and relies on pretrained feature extractors, AV-Link achieves both tasks in a single self-contained framework, directly leveraging features obtained by the complementary modality (i.e. video features to generate audio, or audio features to generate video). Extensive automatic and subjective evaluations demonstrate that our method achieves a substantial improvement in audio-video synchronization, outperforming more expensive baselines such as the MovieGen video-to-audio model.
Text-to-video models have made remarkable advancements through optimization on high-quality text-video pairs, where the textual prompts play a pivotal role in determining quality of output videos. However, achieving the desired output often entails multiple revisions and iterative inference to refine user-provided prompts. Current automatic methods for refining prompts encounter challenges such as Modality-Inconsistency, Cost-Discrepancy, and Model-Unaware when applied to text-to-video diffusion models. To address these problem, we introduce an LLM-based prompt adaptation framework, termed as Prompt-A-Video, which excels in crafting Video-Centric, Labor-Free and Preference-Aligned prompts tailored to specific video diffusion model. Our approach involves a meticulously crafted two-stage optimization and alignment system. Initially, we conduct a reward-guided prompt evolution pipeline to automatically create optimal prompts pool and leverage them for supervised fine-tuning (SFT) of the LLM. Then multi-dimensional rewards are employed to generate pairwise data for the SFT model, followed by the direct preference optimization (DPO) algorithm to further facilitate preference alignment. Through extensive experimentation and comparative analyses, we validate the effectiveness of Prompt-A-Video across diverse generation models, highlighting its potential to push the boundaries of video generation.
Autoregressive models have emerged as a powerful approach for visual generation but suffer from slow inference speed due to their sequential token-by-token prediction process. In this paper, we propose a simple yet effective approach for parallelized autoregressive visual generation that improves generation efficiency while preserving the advantages of autoregressive modeling. Our key insight is that parallel generation depends on visual token dependencies-tokens with weak dependencies can be generated in parallel, while strongly dependent adjacent tokens are difficult to generate together, as their independent sampling may lead to inconsistencies. Based on this observation, we develop a parallel generation strategy that generates distant tokens with weak dependencies in parallel while maintaining sequential generation for strongly dependent local tokens. Our approach can be seamlessly integrated into standard autoregressive models without modifying the architecture or tokenizer. Experiments on ImageNet and UCF-101 demonstrate that our method achieves a 3.6x speedup with comparable quality and up to 9.5x speedup with minimal quality degradation across both image and video generation tasks. We hope this work will inspire future research in efficient visual generation and unified autoregressive modeling. Project page: https://epiphqny.github.io/PAR-project.
Latent diffusion models have made great strides in generating expressive portrait videos with accurate lip-sync and natural motion from a single reference image and audio input. However, these models are far from real-time, often requiring many sampling steps that take minutes to generate even one second of video-significantly limiting practical use. We introduce OSA-LCM (One-Step Avatar Latent Consistency Model), paving the way for real-time diffusion-based avatars. Our method achieves comparable video quality to existing methods but requires only one sampling step, making it more than 10x faster. To accomplish this, we propose a novel avatar discriminator design that guides lip-audio consistency and motion expressiveness to enhance video quality in limited sampling steps. Additionally, we employ a second-stage training architecture using an editing fine-tuned method (EFT), transforming video generation into an editing task during training to effectively address the temporal gap challenge in single-step generation. Experiments demonstrate that OSA-LCM outperforms existing open-source portrait video generation models while operating more efficiently with a single sampling step.