paper-with-me

홈 › Papers

MagicInfinite: Generating Infinite Talking Videos with Your Words and Voice

2025-03-07 · Hongwei Yi, Tian Ye, Shitong Shao, Xuancheng Yang, Jiantong Zhao, Hanzhong Guo, Terrance Wang, Qingyu Yin, Zeke Xie, Lei Zhu, Wei Li, Michael Lingelbach, Daquan Zhou

We present MagicInfinite, a novel diffusion Transformer (DiT) framework that overcomes traditional portrait animation limitations, delivering high-fidelity results across diverse character types-realistic humans, full-body figures, and stylized anime characters. It supports varied facial poses, including back-facing views, and animates single or multiple characters with input masks for precise speaker designation in multi-character scenes. Our approach tackles key challenges with three innovations: (1) 3D full-attention mechanisms with a sliding window denoising strategy, enabling infinite video generation with temporal coherence and visual quality across diverse character styles; (2) a two-stage curriculum learning scheme, integrating audio for lip sync, text for expressive dynamics, and reference images for identity preservation, enabling flexible multi-modal control over long sequences; and (3) region-specific masks with adaptive loss functions to balance global textual control and local audio guidance, supporting speaker-specific animations. Efficiency is enhanced via our innovative unified step and cfg distillation techniques, achieving a 20x inference speed boost over the basemodel: generating a 10 second 540x540p video in 10 seconds or 720x720p in 30 seconds on 8 H100 GPUs, without quality loss. Evaluations on our new benchmark demonstrate MagicInfinite's superiority in audio-lip synchronization, identity preservation, and motion naturalness across diverse scenarios. It is publicly available at https://www.hedra.com/, with examples at https://magicinfinite.github.io/.

📄 PDF Abstract BibTeX arXiv:2503.05978

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingPortrait AnimationVideo Generation

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Talking about what is not there: Generating indefinite referring expressions in Minecraft

2019-10-01 · WS 2019 10 · Arne K{\"o}hn, Alex Koller, er

When generating technical instructions, it is often necessary to describe an object that does not exist yet. For example, an NLG system which explains how to build a house needs to generate sentences like {``}build *a wa…

MinecraftObject

EditYourself: Audio-Driven Generation and Manipulation of Talking Head Videos with Diffusion Transformers

2026-01-29 · John Flynn, Wolfgang Paier, Dimitar Dinev, Sam Nhut Nguyen 외 arxiv

Current generative video models excel at producing novel content from text and image prompts, but leave a critical gap in editing existing pre-recorded videos, where minor alterations to the spoken script require preserv…

Make-Your-Anchor: A Diffusion-based 2D Avatar Generation Framework

2024-03-25 · CVPR 2024 1 · Ziyao Huang, Fan Tang, Yong Zhang, Xiaodong Cun 외

Despite the remarkable process of talking-head-based avatar-creating solutions, directly generating anchor-style videos with full-body motions remains challenging. In this study, we propose Make-Your-Anchor, a novel syst…

Denoising

AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Person

2021-08-09 · Xinsheng Wang, Qicong Xie, Jihua Zhu, Lei Xie 외

Automatically generating videos in which synthesized speech is synchronized with lip movements in a talking head has great potential in many human-computer interaction scenarios. In this paper, we present an automatic me…

Talking Head Generationtext-to-speechText to Speech

EmoGene: Audio-Driven Emotional 3D Talking-Head Generation

2024-10-07 · Wenqing Wang, Yun Fu

Audio-driven talking-head generation is a crucial and useful technology for virtual human interaction and film-making. While recent advances have focused on improving image fidelity and lip synchronization, generating ac…

NeRFTalking Head Generation