STIV: Scalable Text and Image Conditioned Video Generation

• URL: http://arxiv.org/abs/2412.07730v1
• Date: Tue, 10 Dec 2024 18:27:06 GMT
• Title: STIV: Scalable Text and Image Conditioned Video Generation
• Authors: Zongyu Lin, Wei Liu, Chen Chen, Jiasen Lu, Wenze Hu, Tsu-Jui Fu, Jesse Allardice, Zhengfeng Lai, Liangchen Song, Bowen Zhang, Cha Chen, Yiran Fei, Yifan Jiang, Lezhi Li, Yizhou Sun, Kai-Wei Chang, Yinfei Yang,
• Abstract summary: We present a simple and scalable text-image-conditioned video generation method, named STIV. Our framework integrates image condition into a Diffusion Transformer (DiT) through frame replacement, while incorporating text conditioning. STIV can be easily extended to various applications, such as video prediction, frame, multi-view generation, and long video generation.
• Score: 84.2574247093223
• License:
• Abstract: The field of video generation has made remarkable advancements, yet there remains a pressing need for a clear, systematic recipe that can guide the development of robust and scalable models. In this work, we present a comprehensive study that systematically explores the interplay of model architectures, training recipes, and data curation strategies, culminating in a simple and scalable text-image-conditioned video generation method, named STIV. Our framework integrates image condition into a Diffusion Transformer (DiT) through frame replacement, while incorporating text conditioning via a joint image-text conditional classifier-free guidance. This design enables STIV to perform both text-to-video (T2V) and text-image-to-video (TI2V) tasks simultaneously. Additionally, STIV can be easily extended to various applications, such as video prediction, frame interpolation, multi-view generation, and long video generation, etc. With comprehensive ablation studies on T2I, T2V, and TI2V, STIV demonstrate strong performance, despite its simple design. An 8.7B model with 512 resolution achieves 83.1 on VBench T2V, surpassing both leading open and closed-source models like CogVideoX-5B, Pika, Kling, and Gen-3. The same-sized model also achieves a state-of-the-art result of 90.1 on VBench I2V task at 512 resolution. By providing a transparent and extensible recipe for building cutting-edge video generation models, we aim to empower future research and accelerate progress toward more versatile and reliable video generation solutions.

Related papers

• FrameBridge: Improving Image-to-Video Generation with Bridge Models [23.19370431940568]
  Image-to-video (I2V) generation is gaining increasing attention with its wide application in video synthesis. We present FrameBridge, taking the given static image as the prior of video target and establishing a tractable bridge model between them. We propose two techniques, SNR- Fine-tuning (SAF) and neural prior, which improve the fine-tuning efficiency of diffusion-based T2V models to FrameBridge and the synthesis quality of bridge-based I2V models respectively.
  arXiv  Detail & Related papers  (2024-10-20T12:10:24Z)
• xGen-VideoSyn-1: High-fidelity Text-to-Video Synthesis with Compressed Representations [120.52120919834988]
  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.
  arXiv  Detail & Related papers  (2024-08-22T17:55:22Z)
• 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)
• VideoCrafter1: Open Diffusion Models for High-Quality Video Generation [97.5767036934979]
  We introduce two diffusion models for high-quality video generation, namely text-to-video (T2V) and image-to-video (I2V) models. T2V models synthesize a video based on a given text input, while I2V models incorporate an additional image input. Our proposed T2V model can generate realistic and cinematic-quality videos with a resolution of $1024 times 576$, outperforming other open-source T2V models in terms of quality.
  arXiv  Detail & Related papers  (2023-10-30T13:12:40Z)
• LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models [133.088893990272]
  We learn a high-quality text-to-video (T2V) generative model by leveraging a pre-trained text-to-image (T2I) model as a basis. We propose LaVie, an integrated video generation framework that operates on cascaded video latent diffusion models.
  arXiv  Detail & Related papers  (2023-09-26T17:52:03Z)
• Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation [31.882356164068753]
  To reproduce the success of text-to-image (T2I) generation, recent works in text-to-video (T2V) generation employ massive dataset for dataset for T2V generation. We propose Tune-A-Video is capable of producing temporally-coherent videos over various applications.
  arXiv  Detail & Related papers  (2022-12-22T09:43:36Z)
• 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.