EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation

• URL: http://arxiv.org/abs/2507.03905v4
• Date: Thu, 07 Aug 2025 03:40:52 GMT
• Title: EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation
• Authors: Rang Meng, Yan Wang, Weipeng Wu, Ruobing Zheng, Yuming Li, Chenguang Ma,
• Abstract summary: EchoMimicV3 is an efficient framework that unifies multi-task and multi-modal human animation.<n>With a minimal model size of 1.3 billion parameters, EchoMimicV3 achieves competitive performance in both quantitative and qualitative evaluations.
• Score: 8.214084596349744
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent work on human animation usually incorporates large-scale video models, thereby achieving more vivid performance. However, the practical use of such methods is hindered by the slow inference speed and high computational demands. Moreover, traditional work typically employs separate models for each animation task, increasing costs in multi-task scenarios and worsening the dilemma. To address these limitations, we introduce EchoMimicV3, an efficient framework that unifies multi-task and multi-modal human animation. At the core of EchoMimicV3 lies a threefold design: a Soup-of-Tasks paradigm, a Soup-of-Modals paradigm, and a novel training and inference strategy. The Soup-of-Tasks leverages multi-task mask inputs and a counter-intuitive task allocation strategy to achieve multi-task gains without multi-model pains. Meanwhile, the Soup-of-Modals introduces a Coupled-Decoupled Multi-Modal Cross Attention module to inject multi-modal conditions, complemented by a Multi-Modal Timestep Phase-aware Dynamical Allocation mechanism to modulate multi-modal mixtures. Besides, we propose Negative Direct Preference Optimization, Phase-aware Negative Classifier-Free Guidance (CFG), and Long Video CFG, which ensure stable training and inference. Extensive experiments and analyses demonstrate that EchoMimicV3, with a minimal model size of 1.3 billion parameters, achieves competitive performance in both quantitative and qualitative evaluations.

Related papers

• MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings [75.0617088717528]
  MoCa is a framework for transforming pre-trained VLM backbones into effective bidirectional embedding models.<n>MoCa consistently improves performance across MMEB and ViDoRe-v2 benchmarks, achieving new state-of-the-art results.
  arXiv  Detail & Related papers  (2025-06-29T06:41:00Z)
• Multi-identity Human Image Animation with Structural Video Diffusion [64.20452431561436]
  We present Structural Video Diffusion, a novel framework for generating realistic multi-human videos.<n>Our approach introduces identity-specific embeddings to maintain consistent appearances across individuals.<n>We expand existing human video dataset with 25K new videos featuring diverse multi-human and object interaction scenarios.
  arXiv  Detail & Related papers  (2025-04-05T10:03:49Z)
• SM3Det: A Unified Model for Multi-Modal Remote Sensing Object Detection [73.49799596304418]
  This paper introduces a new task called Multi-Modal datasets and Multi-Task Object Detection (M2Det) for remote sensing.<n>It is designed to accurately detect horizontal or oriented objects from any sensor modality.<n>This task poses challenges due to 1) the trade-offs involved in managing multi-modal modelling and 2) the complexities of multi-task optimization.
  arXiv  Detail & Related papers  (2024-12-30T02:47:51Z)
• DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation [54.30327187663316]
  DiTCtrl is a training-free multi-prompt video generation method under MM-DiT architectures for the first time.<n>We analyze MM-DiT's attention mechanism, finding that the 3D full attention behaves similarly to that of the cross/self-attention blocks in the UNet-like diffusion models.<n>Based on our careful design, the video generated by DiTCtrl achieves smooth transitions and consistent object motion given multiple sequential prompts.
  arXiv  Detail & Related papers  (2024-12-24T18:51:19Z)
• AdapMTL: Adaptive Pruning Framework for Multitask Learning Model [5.643658120200373]
  AdapMTL is an adaptive pruning framework for multitask models. It balances sparsity allocation and accuracy performance across multiple tasks. It showcases superior performance compared to state-of-the-art pruning methods.
  arXiv  Detail & Related papers  (2024-08-07T17:19:15Z)
• Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs [67.59291068131438]
  Motion-Agent is a conversational framework designed for general human motion generation, editing, and understanding. Motion-Agent employs an open-source pre-trained language model to develop a generative agent, MotionLLM, that bridges the gap between motion and text.
  arXiv  Detail & Related papers  (2024-05-27T09:57:51Z)
• Towards Multi-Task Multi-Modal Models: A Video Generative Perspective [5.495245220300184]
  This thesis chronicles our endeavor to build multi-task models for generating videos and other modalities under diverse conditions. We unveil a novel approach to mapping bidirectionally between visual observation and interpretable lexical terms. Our scalable visual token representation proves beneficial across generation, compression, and understanding tasks.
  arXiv  Detail & Related papers  (2024-05-26T23:56:45Z)
• Efficient Remote Sensing with Harmonized Transfer Learning and Modality Alignment [0.0]
  "Harmonized Transfer Learning and Modality alignment (HarMA)" is a method that simultaneously satisfies task constraints, modality alignment, and single-modality uniform alignment. HarMA achieves state-of-the-art performance in two popular multimodal retrieval tasks in the field of remote sensing.
  arXiv  Detail & Related papers  (2024-04-28T17:20:08Z)
• Large Motion Model for Unified Multi-Modal Motion Generation [50.56268006354396]
  Large Motion Model (LMM) is a motion-centric, multi-modal framework that unifies mainstream motion generation tasks into a generalist model. LMM tackles these challenges from three principled aspects.
  arXiv  Detail & Related papers  (2024-04-01T17:55:11Z)
• VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis [40.869862603815875]
  VLOGGER is a method for audio-driven human video generation from a single input image. We use a novel diffusion-based architecture that augments text-to-image models with both spatial and temporal controls. We show applications in video editing and personalization.
  arXiv  Detail & Related papers  (2024-03-13T17:59:02Z)
• Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action [46.76487873983082]
  Unified-IO 2 is the first autoregressive multimodal model capable of understanding and generating image, text, audio, and action. We train our model from scratch on a large multimodal pre-training corpus from diverse sources. With a single unified model, Unified-IO 2 achieves state-of-the-art performance on the GRIT benchmark.
  arXiv  Detail & Related papers  (2023-12-28T17:57:06Z)
• Generative Multimodal Models are In-Context Learners [60.50927925426832]
  We introduce Emu2, a generative multimodal model with 37 billion parameters, trained on large-scale multimodal sequences. Emu2 exhibits strong multimodal in-context learning abilities, even emerging to solve tasks that require on-the-fly reasoning.
  arXiv  Detail & Related papers  (2023-12-20T18:59:58Z)
• Improving Efficiency of Diffusion Models via Multi-Stage Framework and Tailored Multi-Decoder Architectures [12.703947839247693]
  Diffusion models, emerging as powerful deep generative tools, excel in various applications. However, their remarkable generative performance is hindered by slow training and sampling. This is due to the necessity of tracking extensive forward and reverse diffusion trajectories. We present a multi-stage framework inspired by our empirical findings to tackle these challenges.
  arXiv  Detail & Related papers  (2023-12-14T17:48:09Z)
• Stochastic Multi-Person 3D Motion Forecasting [21.915057426589744]
  We deal with the ignored real-world complexities in prior work on human motion forecasting. Our framework is general; we instantiate it with different generative models. Our approach produces diverse and accurate multi-person predictions, significantly outperforming the state of the art.
  arXiv  Detail & Related papers  (2023-06-08T17:59:09Z)
• M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design [95.41238363769892]
  Multi-task learning (MTL) encapsulates multiple learned tasks in a single model and often lets those tasks learn better jointly. Current MTL regimes have to activate nearly the entire model even to just execute a single task. We present a model-accelerator co-design framework to enable efficient on-device MTL.
  arXiv  Detail & Related papers  (2022-10-26T15:40:24Z)
• Controllable Dynamic Multi-Task Architectures [92.74372912009127]
  We propose a controllable multi-task network that dynamically adjusts its architecture and weights to match the desired task preference as well as the resource constraints. We propose a disentangled training of two hypernetworks, by exploiting task affinity and a novel branching regularized loss, to take input preferences and accordingly predict tree-structured models with adapted weights.
  arXiv  Detail & Related papers  (2022-03-28T17:56:40Z)

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.