T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design
- URL: http://arxiv.org/abs/2410.05677v2
- Date: Fri, 11 Oct 2024 07:47:36 GMT
- Title: T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design
- Authors: Jiachen Li, Qian Long, Jian Zheng, Xiaofeng Gao, Robinson Piramuthu, Wenhu Chen, William Yang Wang,
- Abstract summary: Our proposed method, T2V-Turbo-v2, introduces a significant advancement by integrating various supervision signals.
We highlight the crucial importance of tailoring datasets to specific learning objectives.
We demonstrate the potential of this approach by extracting motion guidance from the training datasets and incorporating it into the ODE solver.
- Score: 79.7289790249621
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In this paper, we focus on enhancing a diffusion-based text-to-video (T2V) model during the post-training phase by distilling a highly capable consistency model from a pretrained T2V model. Our proposed method, T2V-Turbo-v2, introduces a significant advancement by integrating various supervision signals, including high-quality training data, reward model feedback, and conditional guidance, into the consistency distillation process. Through comprehensive ablation studies, we highlight the crucial importance of tailoring datasets to specific learning objectives and the effectiveness of learning from diverse reward models for enhancing both the visual quality and text-video alignment. Additionally, we highlight the vast design space of conditional guidance strategies, which centers on designing an effective energy function to augment the teacher ODE solver. We demonstrate the potential of this approach by extracting motion guidance from the training datasets and incorporating it into the ODE solver, showcasing its effectiveness in improving the motion quality of the generated videos with the improved motion-related metrics from VBench and T2V-CompBench. Empirically, our T2V-Turbo-v2 establishes a new state-of-the-art result on VBench, with a Total score of 85.13, surpassing proprietary systems such as Gen-3 and Kling.
Related papers
- DSV: Exploiting Dynamic Sparsity to Accelerate Large-Scale Video DiT Training [85.04885553561164]
Diffusion Transformers (DiTs) have shown remarkable performance in modeling and generating high-quality videos.
This paper introduces DSV, a novel framework designed to accelerate and scale the training of video DiTs.
arXiv Detail & Related papers (2025-02-11T14:39:59Z) - Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models [89.79067761383855]
Vchitect-2.0 is a parallel transformer architecture designed to scale up video diffusion models for large-scale text-to-video generation.
By introducing a novel Multimodal Diffusion Block, our approach achieves consistent alignment between text descriptions and generated video frames.
To overcome memory and computational bottlenecks, we propose a Memory-efficient Training framework.
arXiv Detail & Related papers (2025-01-14T21:53:11Z) - ModelGrow: Continual Text-to-Video Pre-training with Model Expansion and Language Understanding Enhancement [49.513401043490305]
This work explores the continual general pre-training of text-to-video models.
We break this task into two key aspects: increasing model capacity and improving semantic understanding.
For semantic understanding, we propose a method that leverages large language models as advanced text encoders.
arXiv Detail & Related papers (2024-12-25T18:58:07Z) - ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation [83.62931466231898]
This paper presents ARLON, a framework that boosts diffusion Transformers with autoregressive models for long video generation.
A latent Vector Quantized Variational Autoencoder (VQ-VAE) compresses the input latent space of the DiT model into compact visual tokens.
An adaptive norm-based semantic injection module integrates the coarse discrete visual units from the AR model into the DiT model.
arXiv Detail & Related papers (2024-10-27T16:28:28Z) - VideoGuide: Improving Video Diffusion Models without Training Through a Teacher's Guide [48.22321420680046]
VideoGuide is a novel framework that enhances the temporal consistency of pretrained text-to-video (T2V) models.
It improves temporal quality by interpolating the guiding model's denoised samples into the sampling model's denoising process.
The proposed method brings about significant improvement in temporal consistency and image fidelity.
arXiv Detail & Related papers (2024-10-06T05:46:17Z) - 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)
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.