Text-driven multi-object image editing which aims to precisely modify multiple objects within an image based on text descriptions, has recently attracted considerable interest. Existing works primarily follow the localize-editing paradigm, focusing on independent object localization and editing while neglecting critical inter-object interactions. However, this work points out that the neglected attention entanglements in inter-object conflict regions, inherently hinder disentangled multi-object editing, leading to either inter-object editing leakage or intra-object editing constraints. We thereby propose a novel multi-layer disentangled editing framework LayerEdit, a training-free method which, for the first time, through precise object-layered decomposition and coherent fusion, enables conflict-free object-layered editing. Specifically, LayerEdit introduces a novel “decompose-editing-fusion” framework, consisting of: (1) Conflict-aware Layer Decomposition module, which utilizes an attention-aware IoU scheme and time-dependent region removing, to enhance conflict awareness and suppression for layer decomposition. (2) Object-layered Editing module, to establish coordinated intra-layer text guidance and cross-layer geometric mapping, achieving disentangled semantic and structural modifications. (3) Transparency-guided Layer Fusion module, to facilitate structure-coherent inter-object layer fusion through precise transparency guidance learning. Extensive experiments verify the superiority of LayerEdit over existing methods, showing unprecedented intra-object controllability and inter-object coherence in complex multi-object scenarios.

Given a text and an image of a specific subject, text-to-image customization aims to generate new images that align with both the text and the subject's appearance. Existing works follow the pseudo-word paradigm, which represents the subject as a non-existent pseudo word and combines it with other text to generate images. However, the pseudo word causes semantic conflict from its different learning objective and entanglement from overlapping influence scopes with other texts, resulting in a dual-optimum paradox where subject similarity and text controllability cannot be optimal simultaneously. To address this, we propose RealCustom++, a novel real-word paradigm that represents the subject with a non-conflicting real word to firstly generate a coherent guidance image and corresponding subject mask, thereby disentangling the influence scopes of the text and subject for simultaneous optimization. Specifically, RealCustom++ introduces a train-inference decoupled framework: (1) during training, it learns a general alignment between visual conditions and all real words in the text; and (2) during inference, a dual-branch architecture is employed, where the Guidance Branch produces the subject guidance mask and the Generation Branch utilizes this mask to customize the generation of the specific real word exclusively within subject-relevant regions. In contrast to previous methods that excel in either controllability or similarity, RealCustom++ achieves superior performance in both, with improvements of 7.48% in controllability, 3.04% in similarity, and 76.43% in generation quality. For multi-subject customization, RealCustom++ further achieves improvements of 4.6% in controllability and 6.34% in multi-subject similarity. Our work has been applied in JiMeng of ByteDance, and codes are released athttps://github.com/bytedance/RealCustom.

Existing generative image transformers follow a two-stage generation paradigm, where the first stage learns a codebook to encode images into discrete codes via vector quantization, and the second stage completes the image generation based on the learned codebook. However, existing methods ignore the naturally varying information densities across different image regions and indiscriminately encode fixed-size regions into fixed-length codes, resulting in insufficient encoding in important regions and redundant encoding in unimportant ones, which degrades both the image generation quality and speed. To address this challenge, we propose a novel information-density-based variable-length image coding and generation framework. In the first stage, our Dynamic Quantization VAE++ (DQVAE++) performs information-adaptive encoding by assigning variable-length codes to image regions according to their information densities, yielding more accurate and robust code representations. In the second stage, the Dynamic Generative Image Transformer (DGiT) enables information-adaptive image generation in both autoregressive and non-autoregressive manners. Specifically, for autoregressive (AR) generation, DGiT-AR generates images autoregressively from coarse-grained regions (smooth areas with fewer codes) to fine-grained regions (detailed areas with more codes). This is accomplished through a novel stacked-transformer architecture that alternately models the position and content of image codes, and a novel heterogeneous embedding scheme to distinguish codes of different granularities. Similarly, for non-autoregressive (NAR) generation, DGiT-NAR introduces a novel information-prioritized mask scheduling mechanism, prioritizing the generation of key structural regions with higher information density. This enables more coherent modeling of global structures initially, followed by a more effective synthesis of local details subsequently. Comprehensive experiments on unconditional and conditional image generation validate the superiority of our proposed variable-length coding in both effectiveness and efficiency.

Subject-driven text-to-image (T2I) customization has drawn significant interest in academia and industry. This task enables pre-trained models to generate novel images based on unique subjects. Existing studies adopt a self-reconstructive perspective, focusing on capturing all details of a single image, which will misconstrue the specific image's irrelevant attributes (e.g., view, pose, and background) as the subject intrinsic attributes. This misconstruction leads to both overfitting or underfitting of irrelevant and intrinsic attributes of the subject, i.e., these attributes are over-represented or under-represented simultaneously, causing a trade-off between similarity and controllability. In this study, we argue an ideal subject representation can be achieved by a cross-differential perspective, i.e., decoupling subject intrinsic attributes from irrelevant attributes via contrastive learning, which allows the model to focus more on intrinsic attributes through intra-consistency (features of the same subject are spatially closer) and inter-distinctiveness (features of different subjects have distinguished differences). Specifically, we propose CustomContrast, a novel framework, which includes a Multilevel Contrastive Learning (MCL) paradigm and a Multimodal Feature Injection (MFI) Encoder. The MCL paradigm is used to extract intrinsic features of subjects from high-level semantics to low-level appearance through crossmodal semantic contrastive learning and multiscale appearance contrastive learning. To facilitate contrastive learning, we introduce the MFI encoder to capture cross-modal representations. Extensive experiments show the effectiveness of CustomContrast in subject similarity and text controllability.

Text-based image editing which aims at generating rigid or non-rigid changes to images conditioned on the given text, has recently attracted considerable interest. Previous works mainly follow the multi-step denoising diffusion paradigm, which adopts a fixed text guidance intensity (i.e., editing intensity) to inject textual features, while ignoring the step-specific editing requirements. This work argues that the editing intensity at each denoising step should be adaptively adjusted conditioned on the historical editing degree, to provide accurate text guidance for the whole denoising process. We thereby propose a novel feedback editing framework (FeedEdit), a training-free method which, explicitly exploits the feedback regulation on editing intensity to ensure precise and harmonious editing at all steps. Specifically, we design (1) Dynamic Editing Degree Perceiving module, which is based on specific frequency-domain filtering, to enhance and exploit the correlation between feature differences and editing degree for perceiving. (2) Proportional-Integral feedback controller, to automatically map the perceived editing errors into appropriate feedback control signals. (3) Phrase-level Regulating Strategy, to achieve fine-grained function-specific regulation of textual features. Extensive experiments demonstrate the superiority of FeedEdit over existing methods in both editability and quality, especially for multi-function editing scenarios.

Interactive drag editing of images is a valuable task that has gained considerable attention for its precision and controllability. However, existing approaches have primarily focused on manipulating the shape or movement of objects in 2D plane. We propose to extend this drag-based editing task to 3D space. Firstly, we utilize the trajectory of two points to represent the rotational trajectory of the object. Gaussian maps of a circle and a square are centered at these two points, respectively. We use distinct shapes to ensure that symmetric views produce different object representations. Secondly, we introduce a lightweight mapping network to embed the object features into two Gaussian maps to obtain a continuous control condition that guides the model in learning the correspondence between the trajectory and the object. Finally, to overcome the limitations of current 3D object reconstruction datasets, which typically consist of object maps with transparent backgrounds, we affix random backgrounds to them. This modification helps improve the model’s ability to ignore background interference when editing real images with complex backgrounds. Experiments demonstrate that our approach successfully achieves object rotation within the drag framework and demonstrates strong generalization to real-world images.

Diffusion models are widely recognized for their ability to generate high-fidelity images. Despite the excellent performance and scalability of the Diffusion Transformer (DiT) architecture, it applies fixed compression across different image regions during the diffusion process, disregarding the naturally varying information densities present in these regions. However, large compression leads to limited local realism, while small compression increases computational complexity and compromises global consistency, ultimately impacting the quality of generated images. To address these limitations, we propose dynamically compressing different image regions by recognizing the importance of different regions, and introduce a novel two-stage framework designed to enhance the effectiveness and efficiency of image generation: (1) Dynamic VAE (DVAE) at first stage employs a hierarchical encoder to encode different image regions at different downsampling rates, tailored to their specific information densities, thereby providing more accurate and natural latent codes for the diffusion process. (2) Dynamic Diffusion Transformer (D2iT) at second stage generates images by predicting multi-grained noise, consisting of coarse-grained (less latent code in smooth regions) and fine-grained (more latent codes in detailed regions), through an novel combination of the Dynamic Grain Transformer and the Dynamic Content Transformer. The strategy of combining rough prediction of noise with detailed regions correction achieves a unification of global consistency and local realism. Comprehensive experiments on various generation tasks validate the effectiveness of our approach. Code will be released at https://github.com/jiawn-creator/Dynamic-DiT.

Large-scale text-to-image models evolve rapidly in size and architecture. The existing adapters struggle to keep pace with these models, requiring extensive retraining. This paper proposes a novel adapter transfer framework, A4A (Adapter for Adapter), which uses an all-for-all mapping approach to seamlessly transfer attention-based adapters across different model architectures (e.g., U-Net to transformer). The framework consists of Coupling Space Projection and Upgraded Space Mapping. During Coupling Space Projection, all attention features of the pretrained adapter are aggregated to fully capture the coupling relationship before being projected into a unified space. The unified space maintains coupling features in a consistent dimension, effectively and efficiently addressing feature scale discrepancies arising from the base model’s architecture. In the Upgraded Space Mapping Module, randomly initialized learnable features are introduced to connect the unified and upgraded spaces by integrating reference features via the attention mechanism. The learned features are adaptively injected into the upgrade model through the Alignment module, which bridges the discrepancies between the models using the all-for-all mapping. Experimental results on personalized image generation tasks demonstrate that A4A outperforms previous methods in transferring adapters while being the first to achieve adapter transfer across model architectures.

Animation colorization is a crucial part of real animation industry production. Long animation colorization has high labor costs. Therefore, automated long animation colorization based on the video generation model has significant research value. Existing studies are limited to short-term colorization. These studies adopt a local paradigm, fusing overlapping features to achieve smooth transitions between local segments. However, the local paradigm neglects global information, failing to maintain long-term color consistency. In this study, we argue that ideal long-term color consistency can be achieved through a dynamic global-local paradigm, i.e., dynamically extracting global color-consistent features relevant to the current generation. Specifically, we propose LongAnimation, a novel framework, which mainly includes a SketchDiT, a Dynamic Global-Local Memory (DGLM), and a Color Consistency Reward. The SketchDiT captures hybrid reference features to support the DGLM module. The DGLM module employs a long video understanding model to dynamically compress global historical features and adaptively fuse them with the current generation features. To refine the color consistency, we introduce a Color Consistency Reward. During inference, we propose a color consistency fusion to smooth the video segment transition. Extensive experiments on both short-term (14 frames) and long-term (average 500 frames) animations show the effectiveness of LongAnimation in maintaining short-term and long-term color consistency for open-domain animation colorization task. The code can be found at https://cn-makers.github.io/long_animation_web/.

Unifying diverse image generation tasks within a single framework remains a fundamental challenge in visual generation. While large language models (LLMs) achieve unification through task-agnostic data and generation, existing visual generation models fail to meet these principles. Current approaches either rely on per-task datasets and large-scale training or adapt pre-trained image models with task-specific modifications, limiting their generalizability. In this work, we explore video models as a foundation for unified image generation, leveraging their inherent ability to model temporal correlations. We introduce RealGeneral, a novel framework that reformulates image generation as a conditional frame prediction task, analogous to in-context learning in LLMs. To bridge the gap between video models and condition-image pairs, we propose (1) a Unified Conditional Embedding module for multi-modal alignment and (2) a Unified Stream DiT Block with decoupled adaptive LayerNorm and attention mask to mitigate cross-modal interference. RealGeneral demonstrates effectiveness in multiple important visual generation tasks, e.g., it achieves a 14.5% improvement in subject similarity for customized generation and a 10% enhancement in image quality for canny-to-image task. Project page: https://lyne1.github.io/RealGeneral/

Customized text-to-video generation with pre-trained large-scale models has recently garnered significant attention through focusing on identity and motion consistency. Existing works typically follow the isolated customized paradigm, where the subject identity or motion dynamics are customized exclusively. However, this paradigm completely ignores the intrinsic mutual constraints and synergistic interdependencies between identity and motion, resulting in identity-motion conflicts throughout the generation process that systematically degrades. To address this, we introduce DualReal, a novel framework that, employs adaptive joint training to collaboratively construct interdependencies between dimensions. Specifically, DualReal is composed of two units: (1) Dual-aware Adaptation dynamically selects a training phase (i.e., identity or motion), learns the current information guided by the frozen dimension prior, and employs a regularization strategy to avoid knowledge leakage; (2) StageBlender Controller leverages the denoising stages and Diffusion Transformer depths to guide different dimensions with adaptive granularity, avoiding conflicts at various stages and ultimately achieving lossless fusion of identity and motion patterns. We constructed a more comprehensive benchmark than existing methods. The experimental results show that DualReal improves CLIP-I and DINO-I metrics by 21.7% and 31.8% on average, and achieves top performance on nearly all motion quality metrics.

Although subject-driven generation has been extensively explored in image generation due to its wide applications, it still has challenges in data scalability and subject expansibility. For the first challenge, moving from curating single-subject datasets to multiple-subject ones and scaling them is particularly difficult. For the second, most recent methods center on single-subject generation, making it hard to apply when dealing with multi-subject scenarios. In this study, we propose a highly-consistent data synthesis pipeline to tackle this challenge. This pipeline harnesses the intrinsic in-context generation capabilities of diffusion transformers and generates high-consistency multi-subject paired data. Additionally, we introduce UNO, which consists of progressive cross-modal alignment and universal rotary position embedding. It is a multi-image conditioned subject-to-image model iteratively trained from a text-to-image model. Extensive experiments show that our method can achieve high consistency while ensuring controllability in both single-subject and multi-subject driven generation.

Text-guided 3D editing aims to precisely edit semantically relevant local 3D regions, which has significant potential for various practical applications ranging from 3D games to film production. Existing methods typically follow a view-indiscriminate paradigm: editing 2D views indiscriminately and projecting them back into 3D space. However, they overlook the different cross-view interdependencies, resulting in inconsistent multi-view editing. In this study, we argue that ideal consistent 3D editing can be achieved through a progressive-views paradigm, which propagates editing semantics from the editing-salient view to other editing-sparse views. Specifically, we propose Pro3D-Editor, a novel framework, which mainly includes Primary-view Sampler, Key-view Render, and Full-view Refiner. Primary-view Sampler dynamically samples and edits the most editing-salient view as the primary view. Key-view Render accurately propagates editing semantics from the primary view to other key views through its Mixture-of-View-Experts Low-Rank Adaption (MoVE-LoRA). Full-view Refiner edits and refines the 3D object based on the edited multi-views. Extensive experiments demonstrate that our method outperforms existing methods in editing accuracy and spatial consistency.

While large-scale pre-trained text-to-image models can synthesize diverse and high-quality human-centric images, an intractable problem is how to preserve the face identity and follow the text prompts simultaneously for conditioned input face images and texts. Despite existing encoder-based methods achieving high efficiency and decent face similarity, the generated image often fails to follow the textual prompts. To ease this editability issue, we present DreamIdentity, to learn edit-friendly and accurate face-identity representations in the word embedding space. Specifically, we propose self-augmented editability learning to enhance the editability for projected embedding, which is achieved by constructing paired generated celebrity's face and edited celebrity images for training, aiming at transferring mature editability of off-the-shelf text-to-image models in celebrity to unseen identities. Furthermore, we design a novel dedicated face-identity encoder to learn an accurate representation of human faces, which applies multi-scale ID-aware features followed by a multi-embedding projector to generate the pseudo words in the text embedding space directly. Extensive experiments show that our method can generate more text-coherent and ID-preserved images with negligible time overhead compared to the standard text-to-image generation process.

GAN-based image attribute editing firstly leverages GAN Inversion to project real images into the latent space of GAN and then manipulates corresponding latent codes. Recent inversion methods mainly utilize additional high-bit features to improve image details preservation, as low-bit codes cannot faithfully reconstruct source images, leading to the loss of details. However, during editing, existing works fail to accurately complement the lost details and suffer from poor editability. The main reason is they inject all the lost details indiscriminately at one time, which inherently induces the position and quantity of details to overfit source images, resulting in inconsistent content and artifacts in edited images. This work argues that details should be gradually injected into both the reconstruction and editing process in a multi-stage coarse-to-fine manner for better detail preservation and high editability. Therefore, a novel dual-stream framework is proposed to accurately complement details at each stage. The Reconstruction Stream is employed to embed coarse-to-fine lost details into residual features and then adaptively add them to the GAN generator. In the Editing Stream, residual features are accurately aligned by our Selective Attention mechanism and then injected into the editing process in a multi-stage manner. Extensive experiments have shown the superiority of our framework in both reconstruction accuracy and editing quality compared with existing methods.

Text-to-image customization, which aims to synthesize text-driven images for the given subjects, has recently rev-olutionized content creation. Existing works follow the pseudo-word paradigm, i.e., represent the given subjects as pseudo-words and then compose them with the given text. However, the inherent entangled influence scope of pseudo-words with the given text results in a dual-optimum para-dox, i.e., the similarity of the given subjects and the con-trollability of the given text could not be optimal simultane-ously. We present RealCustom that, for the first time, dis-entangles similarity from controllability by precisely lim-iting subject influence to relevant parts only, achieved by gradually narrowing real text word from its general conno-tation to the specific subject and using its cross-attention to distinguish relevance. Specifically, RealCustom intro-duces a novel “train-inference” decoupled framework: (1) during training, RealCustom learns general alignment be-tween visual conditions to original textual conditions by a novel adaptive scoring module to adaptively modulate influence quantity; (2) during inference, a novel adaptive mask guidance strategy is proposed to iteratively update the influence scope and influence quantity of the given sub-jects to gradually narrow the generation of the real text word. Comprehensive experiments demonstrate the supe-rior real-time customization ability of RealCustom in the open domain, achieving both unprecedented similarity of the given subjects and controllability of the given text for the first time. The project page is h t tps: / / cor 1 eone-huang.github.io/realcustom

Existing vector quantization (VQ) based autoregressive models follow a two-stage generation paradigm that first learns a codebook to encode images as discrete codes, and then completes generation based on the learned code-book. However, they encode fixed-size image regions into fixed-length codes and ignore their naturally different information densities, which results in insufficiency in important regions and redundancy in unimportant ones, and finally degrades the generation quality and speed. Moreover, the fixed-length coding leads to an unnatural rasterscan autoregressive generation. To address the problem, we propose a novel two-stage framework: (1) Dynamic-Quantization VAE (DQ-VAE) which encodes image regions into variable-length codes based on their information densities for an accurate & compact code representation. (2) DQ-Transformer which thereby generates images autoregressively from coarse-grained (smooth regions with fewer codes) to fine-grained (details regions with more codes) by modeling the position and content of codes in each granularity alternately, through a novel stacked-transformer architecture and shared-content, non-shared position input layers designs. Comprehensive experiments on various generation tasks validate our superiorities in both effectiveness and efficiency. Code will be released at https://github.com/CrossmodalGroup/DynamicVectorQuantization.

Existing autoregressive models follow the two-stage generation paradigm that first learns a codebook in the latent space for image reconstruction and then completes the image generation autoregressively based on the learned codebook. However, existing codebook learning simply models all local region information of images without distinguishing their different perceptual importance, which brings redundancy in the learned codebook that not only limits the next stage's autoregressive model's ability to model important structure but also results in high training cost and slow generation speed. In this study, we borrow the idea of importance perception from classical image coding theory and propose a novel two-stage framework, which consists of Masked Quantization VAE (MQVAE) and Stackformer, to relieve the model from modeling redundancy. Specifically, MQ-VAE incorporates an adaptive mask module for masking redundant region features before quantization and an adaptive de-mask module for recovering the original grid image feature map to faithfully reconstruct the original images after quantization. Then, Stackformer learns to predict the combination of the next code and its position in the feature map. Comprehensive experiments on various image generation validate our effectiveness and efficiency. Code will be released at https://github.com/CrossmodalGroup/MaskedVectorQuantization.

Text-to-image generation aims at generating realistic images which are semantically consistent with the given text. Previous works mainly adopt the multi-stage architecture by stacking generator-discriminator pairs to engage multiple adversarial training, where the text semantics used to provide generation guidance remain static across all stages. This work argues that text features at each stage should be adaptively re-composed conditioned on the status of the historical stage (\emphi.e., historical stage's text and image features) to provide diversified and accurate semantic guidance during the coarse-to-fine generation process. We thereby propose a novel Dynamical Semantic Evolution GAN (DSE-GAN) to re-compose each stage's text features under a novel single adversarial multi-stage architecture. Specifically, we design (1) Dynamic Semantic Evolution (DSE) module, which first aggregates historical image features to summarize the generative feedback, and then dynamically selects words required to be re-composed at each stage as well as re-composed them by dynamically enhancing or suppressing different granularity subspace's semantics. (2) Single Adversarial Multi-stage Architecture (SAMA), which extends the previous structure by eliminating complicated multiple adversarial training requirements and therefore allows more stages of text-image interactions, and finally facilitates the DSE module. We conduct comprehensive experiments and show that DSE-GAN achieves 7.48% and 37.8% relative FID improvement on two widely used benchmarks, i.e., CUB-200 and MSCOCO, respectively.