xGen-VideoSyn-1: High-fidelity Text-to-Video Synthesis with Compressed Representations

• URL: http://arxiv.org/abs/2408.12590v2
• Date: Sat, 31 Aug 2024 05:12:09 GMT
• Title: xGen-VideoSyn-1: High-fidelity Text-to-Video Synthesis with Compressed Representations
• Authors: Can Qin, Congying Xia, Krithika Ramakrishnan, Michael Ryoo, Lifu Tu, Yihao Feng, Manli Shu, Honglu Zhou, Anas Awadalla, Jun Wang, Senthil Purushwalkam, Le Xue, Yingbo Zhou, Huan Wang, Silvio Savarese, Juan Carlos Niebles, Zeyuan Chen, Ran Xu, Caiming Xiong,
• Abstract summary: xGen-SynVideo-1 is a text-to-video (T2V) generation model capable of producing realistic scenes from textual descriptions. VidVAE compresses video data both spatially and temporally, significantly reducing the length of visual tokens. DiT model incorporates spatial and temporal self-attention layers, enabling robust generalization across different timeframes and aspect ratios.
• Score: 120.52120919834988
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present xGen-VideoSyn-1, a text-to-video (T2V) generation model capable of producing realistic scenes from textual descriptions. Building on recent advancements, such as OpenAI's Sora, we explore the latent diffusion model (LDM) architecture and introduce a video variational autoencoder (VidVAE). VidVAE compresses video data both spatially and temporally, significantly reducing the length of visual tokens and the computational demands associated with generating long-sequence videos. To further address the computational costs, we propose a divide-and-merge strategy that maintains temporal consistency across video segments. Our Diffusion Transformer (DiT) model incorporates spatial and temporal self-attention layers, enabling robust generalization across different timeframes and aspect ratios. We have devised a data processing pipeline from the very beginning and collected over 13M high-quality video-text pairs. The pipeline includes multiple steps such as clipping, text detection, motion estimation, aesthetics scoring, and dense captioning based on our in-house video-LLM model. Training the VidVAE and DiT models required approximately 40 and 642 H100 days, respectively. Our model supports over 14-second 720p video generation in an end-to-end way and demonstrates competitive performance against state-of-the-art T2V models.

Related papers

• MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion [3.7270979204213446]
  We present four key contributions to address the challenges of video processing. First, we introduce the 3D Inverted Vector-Quantization Variencoenco Autocoder. Second, we present MotionAura, a text-to-video generation framework. Third, we propose a spectral transformer-based denoising network. Fourth, we introduce a downstream task of Sketch Guided Videopainting.
  arXiv  Detail & Related papers  (2024-10-10T07:07:56Z)
• CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer [55.515836117658985]
  We present CogVideoX, a large-scale text-to-video generation model based on diffusion transformer. It can generate 10-second continuous videos aligned with text prompt, with a frame rate of 16 fps and resolution of 768 * 1360 pixels.
  arXiv  Detail & Related papers  (2024-08-12T11:47:11Z)
• I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models [54.99771394322512]
  Video synthesis has recently made remarkable strides benefiting from the rapid development of diffusion models. It still challenges encounters in terms of semantic accuracy, clarity, and continuity-temporal continuity. We propose a cascaded I2VGen-XL approach that enhances model performance by decoupling these two factors. I2VGen-XL can simultaneously enhance the semantic accuracy, continuity of details and clarity of generated videos.
  arXiv  Detail & Related papers  (2023-11-07T17:16:06Z)
• Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation [55.36617538438858]
  We propose a novel approach that strengthens the interaction between spatial and temporal perceptions. We curate a large-scale and open-source video dataset called HD-VG-130M.
  arXiv  Detail & Related papers  (2023-05-18T11:06:15Z)
• Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models [71.11425812806431]
  Latent Diffusion Models (LDMs) enable high-quality image synthesis while avoiding excessive compute demands. Here, we apply the LDM paradigm to high-resolution generation, a particularly resource-intensive task. We focus on two relevant real-world applications: Simulation of in-the-wild driving data and creative content creation with text-to-video modeling.
  arXiv  Detail & Related papers  (2023-04-18T08:30:32Z)
• Make-A-Video: Text-to-Video Generation without Text-Video Data [69.20996352229422]
  Make-A-Video is an approach for translating the tremendous recent progress in Text-to-Image (T2I) generation to Text-to-Video (T2V) We design a simple yet effective way to build on T2I models with novel and effective spatial-temporal modules. In all aspects, spatial and temporal resolution, faithfulness to text, and quality, Make-A-Video sets the new state-of-the-art in text-to-video generation.
  arXiv  Detail & Related papers  (2022-09-29T13:59:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.