Frame-wise Conditioning Adaptation for Fine-Tuning Diffusion Models in Text-to-Video Prediction

• URL: http://arxiv.org/abs/2503.12953v1
• Date: Mon, 17 Mar 2025 09:06:21 GMT
• Title: Frame-wise Conditioning Adaptation for Fine-Tuning Diffusion Models in Text-to-Video Prediction
• Authors: Zheyuan Liu, Junyan Wang, Zicheng Duan, Cristian Rodriguez-Opazo, Anton van den Hengel,
• Abstract summary: Text-video prediction (TVP) is a downstream video generation task that requires a model to produce subsequent video frames.<n>We propose an adaptation-based strategy we label Frame-wise Conditioning Adaptation (FCA)<n>We use FCA to fine-tune the T2V model, which incorporates the initial frame(s) as an extra condition.
• Score: 36.82594554832902
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-video prediction (TVP) is a downstream video generation task that requires a model to produce subsequent video frames given a series of initial video frames and text describing the required motion. In practice TVP methods focus on a particular category of videos depicting manipulations of objects carried out by human beings or robot arms. Previous methods adapt models pre-trained on text-to-image tasks, and thus tend to generate video that lacks the required continuity. A natural progression would be to leverage more recent pre-trained text-to-video (T2V) models. This approach is rendered more challenging by the fact that the most common fine-tuning technique, low-rank adaptation (LoRA), yields undesirable results. In this work, we propose an adaptation-based strategy we label Frame-wise Conditioning Adaptation (FCA). Within the module, we devise a sub-module that produces frame-wise text embeddings from the input text, which acts as an additional text condition to aid generation. We use FCA to fine-tune the T2V model, which incorporates the initial frame(s) as an extra condition. We compare and discuss the more effective strategy for injecting such embeddings into the T2V model. We conduct extensive ablation studies on our design choices with quantitative and qualitative performance analysis. Our approach establishes a new state-of-the-art for the task of TVP. The project page is at https://github.com/Cuberick-Orion/FCA .

Related papers

• STIV: Scalable Text and Image Conditioned Video Generation [84.2574247093223]
  We present a simple and scalable text-image-conditioned video generation method, named STIV.<n>Our framework integrates image condition into a Diffusion Transformer (DiT) through frame replacement, while incorporating text conditioning.<n> STIV can be easily extended to various applications, such as video prediction, frame, multi-view generation, and long video generation.
  arXiv  Detail & Related papers  (2024-12-10T18:27:06Z)
• 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)
• AID: Adapting Image2Video Diffusion Models for Instruction-guided Video Prediction [88.70116693750452]
  Text-guided video prediction (TVP) involves predicting the motion of future frames from the initial frame according to an instruction. Previous TVP methods make significant breakthroughs by adapting Stable Diffusion for this task. We introduce the Multi-Modal Large Language Model (MLLM) to predict future video states based on initial frames and text instructions.
  arXiv  Detail & Related papers  (2024-06-10T17:02:08Z)
• Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation [72.90144343056227]
  We explore the visual representations produced from a pre-trained text-to-video (T2V) diffusion model for video understanding tasks. We introduce a novel framework, termed "VD-IT", tailored with dedicatedly designed components built upon a fixed T2V model. Our VD-IT achieves highly competitive results, surpassing many existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-03-18T17:59:58Z)
• ConditionVideo: Training-Free Condition-Guided Text-to-Video Generation [33.37279673304]
  We introduce ConditionVideo, a training-free approach to text-to-video generation based on the provided condition, video, and input text. ConditionVideo generates realistic dynamic videos from random noise or given scene videos. Our method exhibits superior performance in terms of frame consistency, clip score, and conditional accuracy, outperforming other compared methods.
  arXiv  Detail & Related papers  (2023-10-11T17:46:28Z)
• Control-A-Video: Controllable Text-to-Video Diffusion Models with Motion Prior and Reward Feedback Learning [50.60891619269651]
  Control-A-Video is a controllable T2V diffusion model that can generate videos conditioned on text prompts and reference control maps like edge and depth maps. We propose novel strategies to incorporate content prior and motion prior into the diffusion-based generation process. Our framework generates higher-quality, more consistent videos compared to existing state-of-the-art methods in controllable text-to-video generation.
  arXiv  Detail & Related papers  (2023-05-23T09:03:19Z)
• LiteVL: Efficient Video-Language Learning with Enhanced Spatial-Temporal Modeling [48.283659682112926]
  We propose LiteVL, which adapts a pre-trained image-language model BLIP into a video-text model directly on downstream tasks. We also propose a non-parametric pooling mechanism to adaptively reweight the fine-grained video embedding conditioned on the text.
  arXiv  Detail & Related papers  (2022-10-21T13:03:49Z)
• 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)
• Align and Prompt: Video-and-Language Pre-training with Entity Prompts [111.23364631136339]
  Video-and-language pre-training has shown promising improvements on various downstream tasks. We propose Align and Prompt: an efficient and effective video-and-language pre-training framework with better cross-modal alignment. Our code and pre-trained models will be released.
  arXiv  Detail & Related papers  (2021-12-17T15:55:53Z)

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.