# RealisDance-DiT: Simple yet Strong Baseline towards Controllable Character Animation in the Wild

arXiv: https://arxiv.org/abs/2504.14977 · HTML: https://mlsanity.com/paper/2504.14977/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 35 references that are in the map.
- First posted on arXiv 21 Apr 2025.

## Builds on (most cited first, 30 of 30)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [First Order Motion Model for Image Animation](https://mlsanity.com/paper/2003.00196/) (2020)
- [Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation](https://mlsanity.com/paper/2311.17117/) (2023)
- [VACE: All-in-One Video Creation and Editing](https://mlsanity.com/paper/2503.07598/) (2025)
- [MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model](https://mlsanity.com/paper/2311.16498/) (2023)
- [Effective Whole-body Pose Estimation with Two-stages Distillation](https://mlsanity.com/paper/2307.15880/) (2023)
- [Reconstructing Hands in 3D with Transformers](https://mlsanity.com/paper/2312.05251/) (2023)
- [Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance](https://mlsanity.com/paper/2403.14781/) (2024)
- [Motion Representations for Articulated Animation](https://mlsanity.com/paper/2104.11280/) (2021)
- [Efficient Diffusion Training via Min-SNR Weighting Strategy](https://mlsanity.com/paper/2303.09556/) (2023)
- [MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance](https://mlsanity.com/paper/2406.19680/) (2024)
- [ControlNeXt: Powerful and Efficient Control for Image and Video Generation](https://mlsanity.com/paper/2408.06070/) (2024)
- [DisCo: Disentangled Control for Realistic Human Dance Generation](https://mlsanity.com/paper/2307.00040/) (2023)
- [World-Grounded Human Motion Recovery via Gravity-View Coordinates](https://mlsanity.com/paper/2409.06662/) (2024)
- [OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models](https://mlsanity.com/paper/2502.01061/) (2025)
- [DwNet: Dense warp-based network for pose-guided human video generation](https://mlsanity.com/paper/1910.09139/) (2019)
- [Animate-X: Universal Character Image Animation with Enhanced Motion Representation](https://mlsanity.com/paper/2410.10306/) (2024)
- [HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation](https://mlsanity.com/paper/2407.17438/) (2024)
- [Animate Anyone 2: High-Fidelity Character Image Animation with Environment Affordance](https://mlsanity.com/paper/2502.06145/) (2025)
- [HumanDiT: Pose-Guided Diffusion Transformer for Long-form Human Motion Video Generation](https://mlsanity.com/paper/2502.04847/) (2025)
- [RealisDance: Equip controllable character animation with realistic hands](https://mlsanity.com/paper/2409.06202/) (2024)
- [A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training](https://mlsanity.com/paper/2405.17403/) (2024)
- [Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment](https://mlsanity.com/paper/2406.12303/) (2024)

## Built on by (most cited first, 29 of 29)

- [Wan-Animate: Unified Character Animation and Replacement with Holistic Replication](https://mlsanity.com/paper/2509.14055/) (2025)
- [FLUX-Text: A Simple and Advanced Diffusion Transformer Baseline for Scene Text Editing](https://mlsanity.com/paper/2505.03329/) (2025)
- [SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations](https://mlsanity.com/paper/2512.05905/) (2025)
- [EchoMotion: Unified Human Video and Motion Generation via Dual-Modality Diffusion Transformer](https://mlsanity.com/paper/2512.18814/) (2025)
- [RealisMotion: Decomposed Human Motion Control and Video Generation in the World Space](https://mlsanity.com/paper/2508.08588/) (2025)
- [SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation](https://mlsanity.com/paper/2511.19320/) (2025)
- [PoseGen: In-Context LoRA Finetuning for Pose-Controllable Long Human Video Generation](https://mlsanity.com/paper/2508.05091/) (2025)
- [ByteLoom: Weaving Geometry-Consistent Human-Object Interactions through Progressive Curriculum Learning](https://mlsanity.com/paper/2512.22854/) (2025)
- [CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos](https://mlsanity.com/paper/2601.10632/) (2026)
- [OmniTransfer: All-in-one Framework for Spatio-temporal Video Transfer](https://mlsanity.com/paper/2601.14250/) (2026)
- [Directing the World: Fast Autoregressive Video Generation with Compositional Human-Camera Control](https://mlsanity.com/paper/2606.27964/) (2026)
- [EditCtrl: Disentangled Local and Global Control for Real-Time Generative Video Editing](https://mlsanity.com/paper/2602.15031/) (2026)
- [MTVCraft: Tokenizing 4D Motion for Arbitrary Character Animation](https://mlsanity.com/paper/2505.10238/) (2025)
- [MotionWeaver: Holistic 4D-Anchored Framework for Multi-Humanoid Image Animation](https://mlsanity.com/paper/2602.13326/) (2026)
- [EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration](https://mlsanity.com/paper/2605.15042/) (2026)
- [AHOY! Animatable Humans under Occlusion from YouTube Videos with Gaussian Splatting and Video Diffusion Priors](https://mlsanity.com/paper/2603.17975/) (2026)
- [High-Fidelity and Long-Duration Human Image Animation with Diffusion Transformer](https://mlsanity.com/paper/2512.21905/) (2025)
- [IM-Animation: An Implicit Motion Representation for Identity-decoupled Character Animation](https://mlsanity.com/paper/2602.07498/) (2026)
- [Towards 3D-Aware Video Diffusion Models: Render-Free Human Motion Control with Mesh Tokenization](https://mlsanity.com/paper/2606.02000/) (2026)
- [Generating Fit Check Videos with a Handheld Camera](https://mlsanity.com/paper/2505.23886/) (2025)
- [DISPLAY: Directable Human-Object Interaction Video Generation via Sparse Motion Guidance and Multi-Task Auxiliary](https://mlsanity.com/paper/2603.09883/) (2026)
- [AnyCrowd: Instance-Isolated Identity-Pose Binding for Arbitrary Multi-Character Animation](https://mlsanity.com/paper/2603.15415/) (2026)
- [ONE-SHOT: Compositional Human-Environment Video Synthesis via Spatial-Decoupled Motion Injection and Hybrid Context Integration](https://mlsanity.com/paper/2604.01043/) (2026)
- [ActCam: Zero-Shot Joint Camera and 3D Motion Control for Video Generation](https://mlsanity.com/paper/2605.06667/) (2026)
- [EMOSH: Expressive Motion and Shape Disentanglement for Human Animation](https://mlsanity.com/paper/2606.28026/) (2026)
- [3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement](https://mlsanity.com/paper/2606.30514/) (2026)
- [UniMoCa: Unifying Motion and Camera Controls as Visual Proxies for Faithful Human Video Generation](https://mlsanity.com/paper/2608.01944/) (2026)
- [Human-Centric Intelligence in the Era of Foundation Models: A Survey](https://mlsanity.com/paper/2608.18184/) (2026)
- [RASA: Disentangled Spatial-Motional Priors for Cross-Identity Character Animation](https://mlsanity.com/paper/2608.28219/) (2026)

## Abstract (arXiv)

Controllable character animation remains a challenging problem, particularly in handling rare poses, stylized characters, character-object interactions, complex illumination, and dynamic scenes. To tackle these issues, prior work has largely focused on injecting pose and appearance guidance via elaborate bypass networks, but often struggles to generalize to open-world scenarios. In this paper, we propose a new perspective that, as long as the foundation model is powerful enough, straightforward model modifications with flexible fine-tuning strategies can largely address the above challenges, taking a step towards controllable character animation in the wild. Specifically, we introduce RealisDance-DiT, built upon the Wan-2.1 video foundation model. Our sufficient analysis reveals that the widely adopted Reference Net design is suboptimal for large-scale DiT models. Instead, we demonstrate that minimal modifications to the foundation model architecture yield a surprisingly strong baseline. We further propose the low-noise warmup and "large batches and small iterations" strategies to accelerate model convergence during fine-tuning while maximally preserving the priors of the foundation model. In addition, we introduce a new test dataset that captures diverse real-world challenges, complementing existing benchmarks such as TikTok dataset and UBC fashion video dataset, to comprehensively evaluate the proposed method. Extensive experiments show that RealisDance-DiT outperforms existing methods by a large margin.