DynamiCtrl: Rethinking the Basic Structure and the Role of Text for High-quality Human Image Animation

• URL: http://arxiv.org/abs/2503.21246v2
• Date: Sun, 18 May 2025 16:24:19 GMT
• Title: DynamiCtrl: Rethinking the Basic Structure and the Role of Text for High-quality Human Image Animation
• Authors: Haoyu Zhao, Zhongang Qi, Cong Wang, Qingping Zheng, Guansong Lu, Fei Chen, Hang Xu, Zuxuan Wu,
• Abstract summary: We propose DynamiCtrl, a novel framework for human animation in video DiT architecture.<n>We use a shared VAE encoder for human images and driving poses, unifying them into a common latent space.<n>We also introduce the "Joint-text" paradigm, which preserves the role of text embeddings to provide global semantic context.
• Score: 63.781450025764904
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With diffusion transformer (DiT) excelling in video generation, its use in specific tasks has drawn increasing attention. However, adapting DiT for pose-guided human image animation faces two core challenges: (a) existing U-Net-based pose control methods may be suboptimal for the DiT backbone; and (b) removing text guidance, as in previous approaches, often leads to semantic loss and model degradation. To address these issues, we propose DynamiCtrl, a novel framework for human animation in video DiT architecture. Specifically, we use a shared VAE encoder for human images and driving poses, unifying them into a common latent space, maintaining pose fidelity, and eliminating the need for an expert pose encoder during video denoising. To integrate pose control into the DiT backbone effectively, we propose a novel Pose-adaptive Layer Norm model. It injects normalized pose features into the denoising process via conditioning on visual tokens, enabling seamless and scalable pose control across DiT blocks. Furthermore, to overcome the shortcomings of text removal, we introduce the "Joint-text" paradigm, which preserves the role of text embeddings to provide global semantic context. Through full-attention blocks, image and pose features are aligned with text features, enhancing semantic consistency, leveraging pretrained knowledge, and enabling multi-level control. Experiments verify the superiority of DynamiCtrl on benchmark and self-collected data (e.g., achieving the best LPIPS of 0.166), demonstrating strong character control and high-quality synthesis. The project page is available at https://gulucaptain.github.io/DynamiCtrl/.

Related papers

• DyST-XL: Dynamic Layout Planning and Content Control for Compositional Text-to-Video Generation [14.34140569565309]
  DyST-XL is a framework that enhances off-the-shelf text-to-video models through frame-aware control. The code is released in https://github.com/XiaoBuL/DyST-XL.
  arXiv  Detail & Related papers  (2025-04-21T11:41:22Z)
• Context Canvas: Enhancing Text-to-Image Diffusion Models with Knowledge Graph-Based RAG [6.701537544179892]
  We introduce a novel approach to enhance the capabilities of text-to-image models by incorporating a graph-based RAG.<n>Our system dynamically retrieves detailed character information and relational data from the knowledge graph, enabling the generation of visually accurate and contextually rich images.
  arXiv  Detail & Related papers  (2024-12-12T18:59:41Z)
• FBSDiff: Plug-and-Play Frequency Band Substitution of Diffusion Features for Highly Controllable Text-Driven Image Translation [19.65838242227773]
  This paper contributes a novel, concise, and efficient approach that adapts pre-trained large-scale text-to-image (T2I) diffusion model to the image-to-image (I2I) paradigm in a plug-and-play manner. Our method allows flexible control over both guiding factor and guiding intensity of the reference image simply by tuning the type and bandwidth of the substituted frequency band.
  arXiv  Detail & Related papers  (2024-08-02T04:13:38Z)
• STAR: Scale-wise Text-conditioned AutoRegressive image generation [38.98271279816512]
  We introduce STAR, a text-to-image model that employs a scale-wise auto-regressive paradigm.<n> STAR enables text-driven image generation up to 1024$times$1024 through three key designs.
  arXiv  Detail & Related papers  (2024-06-16T03:45:45Z)
• Zero-shot High-fidelity and Pose-controllable Character Animation [89.74818983864832]
  Image-to-video (I2V) generation aims to create a video sequence from a single image. Existing approaches suffer from inconsistency of character appearances and poor preservation of fine details. We propose PoseAnimate, a novel zero-shot I2V framework for character animation.
  arXiv  Detail & Related papers  (2024-04-21T14:43:31Z)
• LASER: Tuning-Free LLM-Driven Attention Control for Efficient Text-conditioned Image-to-Animation [52.16008431411513]
  LASER is a tuning-free LLM-driven attention control framework.<n>We propose a Text-conditioned Image-to-Animation Benchmark to validate the effectiveness and efficacy of LASER.
  arXiv  Detail & Related papers  (2024-04-21T07:13:56Z)
• SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models [84.71887272654865]
  We present SparseCtrl to enable flexible structure control with temporally sparse signals. It incorporates an additional condition to process these sparse signals while leaving the pre-trained T2V model untouched. The proposed approach is compatible with various modalities, including sketches, depth maps, and RGB images.
  arXiv  Detail & Related papers  (2023-11-28T16:33:08Z)
• Enhancing Diffusion Models with Text-Encoder Reinforcement Learning [63.41513909279474]
  Text-to-image diffusion models are typically trained to optimize the log-likelihood objective. Recent research addresses this issue by refining the diffusion U-Net using human rewards through reinforcement learning or direct backpropagation. We demonstrate that by finetuning the text encoder through reinforcement learning, we can enhance the text-image alignment of the results.
  arXiv  Detail & Related papers  (2023-11-27T09:39:45Z)
• TVTSv2: Learning Out-of-the-box Spatiotemporal Visual Representations at Scale [59.01246141215051]
  We analyze the factor that leads to degradation from the perspective of language supervision. We propose a tunable-free pre-training strategy to retain the generalization ability of the text encoder. We produce a series of models, dubbed TVTSv2, with up to one billion parameters.
  arXiv  Detail & Related papers  (2023-05-23T15:44:56Z)
• LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model [55.20469538848806]
  LeftRefill is an innovative approach to harness large Text-to-Image (T2I) diffusion models for reference-guided image synthesis. This paper introduces LeftRefill, an innovative approach to efficiently harness large Text-to-Image (T2I) diffusion models for reference-guided image synthesis.
  arXiv  Detail & Related papers  (2023-05-19T10:29:42Z)
• Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation [10.39028769374367]
  We present a new framework that takes text-to-image synthesis to the realm of image-to-image translation. Our method harnesses the power of a pre-trained text-to-image diffusion model to generate a new image that complies with the target text.
  arXiv  Detail & Related papers  (2022-11-22T20:39:18Z)
• eDiffi: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers [87.52504764677226]
  Large-scale diffusion-based generative models have led to breakthroughs in text-conditioned high-resolution image synthesis. We train an ensemble of text-to-image diffusion models specialized for different stages synthesis. Our ensemble of diffusion models, called eDiffi, results in improved text alignment while maintaining the same inference cost.
  arXiv  Detail & Related papers  (2022-11-02T17:43:04Z)
• DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation [56.514462874501675]
  We propose a dynamic sparse attention based Transformer model to achieve fine-level matching with favorable efficiency. The heart of our approach is a novel dynamic-attention unit, dedicated to covering the variation on the optimal number of tokens one position should focus on. Experiments on three applications, pose-guided person image generation, edge-based face synthesis, and undistorted image style transfer, demonstrate that DynaST achieves superior performance in local details.
  arXiv  Detail & Related papers  (2022-07-13T11:12:03Z)
• Scaling Autoregressive Models for Content-Rich Text-to-Image Generation [95.02406834386814]
  Parti treats text-to-image generation as a sequence-to-sequence modeling problem. Parti uses a Transformer-based image tokenizer, ViT-VQGAN, to encode images as sequences of discrete tokens. PartiPrompts (P2) is a new holistic benchmark of over 1600 English prompts.
  arXiv  Detail & Related papers  (2022-06-22T01:11:29Z)
• Pose Guided Multi-person Image Generation From Text [15.15576618501609]
  Existing methods struggle to create high fidelity full-body images, especially multiple people. We propose a pose-guided text-to-image model, using pose as an additional input constraint. We show results on the Deepfashion dataset and create a new multi-person Deepfashion dataset to demonstrate the multi-capabilities of our approach.
  arXiv  Detail & Related papers  (2022-03-09T17:38:03Z)
• Cycle-Consistent Inverse GAN for Text-to-Image Synthesis [101.97397967958722]
  We propose a novel unified framework of Cycle-consistent Inverse GAN for both text-to-image generation and text-guided image manipulation tasks. We learn a GAN inversion model to convert the images back to the GAN latent space and obtain the inverted latent codes for each image. In the text-guided optimization module, we generate images with the desired semantic attributes by optimizing the inverted latent codes.
  arXiv  Detail & Related papers  (2021-08-03T08:38:16Z)
• Controllable Person Image Synthesis with Spatially-Adaptive Warped Normalization [72.65828901909708]
  Controllable person image generation aims to produce realistic human images with desirable attributes. We introduce a novel Spatially-Adaptive Warped Normalization (SAWN), which integrates a learned flow-field to warp modulation parameters. We propose a novel self-training part replacement strategy to refine the pretrained model for the texture-transfer task.
  arXiv  Detail & Related papers  (2021-05-31T07:07:44Z)
• Improving Generation and Evaluation of Visual Stories via Semantic Consistency [72.00815192668193]
  Given a series of natural language captions, an agent must generate a sequence of images that correspond to the captions. Prior work has introduced recurrent generative models which outperform synthesis text-to-image models on this task. We present a number of improvements to prior modeling approaches, including the addition of a dual learning framework.
  arXiv  Detail & Related papers  (2021-05-20T20:42:42Z)
• Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation [96.66010515343106]
  We propose a clean yet effective framework to generate pose-controllable talking faces. We operate on raw face images, using only a single photo as an identity reference. Our model has multiple advanced capabilities including extreme view robustness and talking face frontalization.
  arXiv  Detail & Related papers  (2021-04-22T15:10:26Z)

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.