mlsanityData to 7 Oct 2026

StyleMotif: Multi-Modal Motion Stylization using Style-Content Cross Fusion

arXiv 2503.21775 ↗First posted 27 Mar 2025cs.CV cs.AI cs.CLcited by 7

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

We present StyleMotif, a novel Stylized Motion Latent Diffusion model, generating motion conditioned on both content and style from multiple modalities. Unlike existing approaches that either focus on generating diverse motion content or transferring style from sequences, StyleMotif seamlessly synthesizes motion across a wide range of content while incorporating stylistic cues from multi-modal inputs, including motion, text, image, video, and audio. To achieve this, we introduce a style-content cross fusion mechanism and align a style encoder with a pre-trained multi-modal model, ensuring that the generated motion accurately captures the reference style while preserving realism. Extensive experiments demonstrate that our framework surpasses existing methods in stylized motion generation and exhibits emergent capabilities for multi-modal motion stylization, enabling more nuanced motion synthesis. Source code and pre-trained models will be released upon acceptance. Project Page: https://stylemotif.github.io

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 64 of its 77 references that are in the map. First posted on arXiv 27 Mar 2025.

Builds on

64 of 77 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024SMooDi: Stylized Motion Diffusion Model17 Jul
  2. 2023Adding Conditional Control to Text-to-Image Diffusion Models10 Feb
  3. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Models17 Nov

Other references · 61

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  4. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  5. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,162
  6. 2022Human Motion Diffusion Modelcited by 1,062
  7. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 768
  8. 2023LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Modelcited by 602
  9. 2024MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?cited by 573
  10. 2024LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Modelscited by 571
  11. 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 567
  12. 2023MotionGPT: Human Motion as a Foreign Languagecited by 521
38 more
  1. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 461
  2. 2023MoMask: Generative Masked Modeling of 3D Human Motionscited by 388
  3. 2023LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignmentcited by 366
  4. 2022PhysDiff: Physics-Guided Human Motion Diffusion Modelcited by 365
  5. 2022Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classificationcited by 355
  6. 2020VirTex: Learning Visual Representations from Textual Annotationscited by 338
  7. 2022ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understandingcited by 262
  8. 2023Diffusion-based Generation, Optimization, and Planning in 3D Scenescited by 237
  9. 2023OmniControl: Control Any Joint at Any Time for Human Motion Generationcited by 233
  10. 2021CLIP2Video: Mastering Video-Text Retrieval via Image CLIPcited by 223
  11. 2023Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Followingcited by 192
  12. 2022PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learningcited by 186
  13. 2023InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusioncited by 181
  14. 2024MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Modelcited by 164
  15. 2023ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulationcited by 157
  16. 2017Demystifying Neural Style Transfercited by 152
  17. 2023ImageBind-LLM: Multi-modality Instruction Tuningcited by 142
  18. 2023Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusioncited by 137
  19. 2025Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Stepcited by 130
  20. 2023MMM: Generative Masked Motion Modelcited by 129
  21. 2025MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiencycited by 123
  22. 2024MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Enginecited by 111
  23. 2022CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attentioncited by 103
  24. 2023LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understandingcited by 95
  25. 2020Unpaired Motion Style Transfer from Video to Animationcited by 94
  26. 2023TLControl: Trajectory and Language Control for Human Motion Synthesiscited by 93
  27. 2023HOI-Diff: Text-Driven Synthesis of 3D Human-Object Interactions using Diffusion Modelscited by 89
  28. 2024MotionLLM: Understanding Human Behaviors from Human Motions and Videoscited by 89
  29. 2024Multi-Track Timeline Control for Text-Driven 3D Human Motion Generationcited by 88
  30. 2022Learning Audio-Video Modalities from Image Captionscited by 80
  31. 2022Real-Time Style Modelling of Human Locomotion via Feature-Wise Transformations and Local Motion Phasescited by 71
  32. 2023Single Motion Diffusioncited by 65
  33. 2022Motion Puzzle: Arbitrary Motion Style Transfer by Body Partcited by 64
  34. 2024InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interactioncited by 63
  35. 2024DiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Textual Descriptionscited by 60
  36. 2024LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioningcited by 58
  37. 2024BAMM: Bidirectional Autoregressive Motion Modelcited by 54
  38. 2024Generating Human Motion in 3D Scenes from Text Descriptionscited by 49

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 5.

7 papers.

  1. 2025Behave Your Motion: Habit-preserved Cross-category Animal Motion Transfercited by 1
  2. 2025ClusterStyle: Modeling Intra-Style Diversity with Prototypical Clustering for Stylized Motion Generationcited by 1
  3. 2026MoSAIC: Aligned Intervention Supervision for Part-Local Motion Style Transfercited by 0
  4. 2026Flexible Motion Generation from Language and Style Referencescited by 0
  5. 2026MorphoStyle: Motion Style Transfer with Morphology Controlcited by 0
  6. 2026VISTA: Video-Injected Stylized Text-to-Animationcited by 0
  7. 2026Motion Style Slider: Endpoint-Supervised Continuous Style Control for Human Motion Diffusioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Stylized Text-to-Motion Generation via Hypernetwork-Driven Low-Rank Adaptation
  2. 2024Diffusion-based Human Motion Style Transfer with Semantic Guidance
  3. 2024SMCD: High Realism Motion Style Transfer via Mamba-based Diffusion
  4. 2022Unifying Human Motion Synthesis and Style Transfer with Denoising Diffusion Probabilistic Models
  5. 2025SOYO: A Tuning-Free Approach for Video Style Morphing via Style-Adaptive Interpolation in Diffusion Models
  6. 2026VISTA: Triplet-Supervised Video Style Transfer with Diffusion Transformers
  7. 2025SMooGPT: Stylized Motion Generation using Large Language Models
  8. 2023Style-A-Video: Agile Diffusion for Arbitrary Text-based Video Style Transfer