No article text was recorded for this version.
decoupled cross-attention
Version 1 of 166 papers89 conceptsfrozen 2026-10-04
Papers in this version
- Blog: FonTS: Text Rendering With Typography and Style Controls
- Blog: CSGO: Content-Style Composition in Text-to-Image Generation
- Blog: AlignedGen: Aligning Style Across Generated Images
- Blog: Arbitrary Style Transfer via Multi-Adaptation Network
- Blog: GRIF-DM: Generation of Rich Impression Fonts using Diffusion Models
- Blog: ArtAdapter: Text-to-Image Style Transfer using Multi-Level Style Encoder and Explicit Adaptation
- Blog: ID-Animator: Zero-Shot Identity-Preserving Human Video Generation
- Blog: CustomNet: Zero-shot Object Customization with Variable-Viewpoints in Text-to-Image Diffusion Models
- Blog: RelationAdapter: Learning and Transferring Visual Relation with Diffusion Transformers
- Blog: AnyMS: Bottom-up Attention Decoupling for Layout-guided and Training-free Multi-subject Customization
- Blog: Tuning-Free Adaptive Style Incorporation for Structure-Consistent Text-Driven Style Transfer
- Blog: PortraitTalk: Towards Customizable One-Shot Audio-to-Talking Face Generation
- Blog: Audio Prompt Adapter: Unleashing Music Editing Abilities for Text-to-Music with Lightweight Finetuning
- Blog: Visual Persona: Foundation Model for Full-Body Human Customization
- Blog: Att-Adapter: A Robust and Precise Domain-Specific Multi-Attributes T2I Diffusion Adapter via Conditional Variational Autoencoder
- Blog: LoopAnimate: Loopable Salient Object Animation
- Blog: CreativeSynth: Creative Blending and Synthesis of Visual Arts based on Multimodal Diffusion
- Blog: RB-Modulation: Training-Free Stylization using Reference-Based Modulation
- Blog: ViscoNet: Bridging and Harmonizing Visual and Textual Conditioning for ControlNet
- Blog: Neural Scene Designer: Self-Styled Semantic Image Manipulation
- Blog: Learning A Low-Level Vision Generalist via Visual Task Prompt
- Blog: ConsisSR: Delving Deep into Consistency in Diffusion-based Image Super-Resolution
- Blog: Devil is in the Detail: Towards Injecting Fine Details of Image Prompt in Image Generation via Conflict-free Guidance and Stratified Attention
- Blog: Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer
- Blog: Controllable 3D Face Generation with Conditional Style Code Diffusion
- Blog: EVEv2: Improved Baselines for Encoder-Free Vision-Language Models
- Blog: Personalized Face Inpainting with Diffusion Models by Parallel Visual Attention
- Blog: UVMap-ID: A Controllable and Personalized UV Map Generative Model
- Blog: InstantID: Zero-shot Identity-Preserving Generation in Seconds
- Blog: Flash-Split: 2D Reflection Removal with Flash Cues and Latent Diffusion Separation
- Blog: PS-Diffusion: Photorealistic Subject-Driven Image Editing with Disentangled Control and Attention
- Blog: SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation
- Blog: MoA: Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation
- Blog: StyleAdapter: A Unified Stylized Image Generation Model
- Blog: Puff-Net: Efficient Style Transfer with Pure Content and Style Feature Fusion Network
- Blog: InsightEdit: Towards Better Instruction Following for Image Editing
- Blog: Controllable 3D Face Generation with Conditional Style Code Diffusion
- Blog: ClusterStyle: Modeling Intra-Style Diversity with Prototypical Clustering for Stylized Motion Generation
- Blog: MasterWeaver: Taming Editability and Face Identity for Personalized Text-to-Image Generation
- Blog: GarmentDiffusion: 3D Garment Sewing Pattern Generation with Multimodal Diffusion Transformers
- Blog: CreativeSynth: Cross-Art-Attention for Artistic Image Synthesis With Multimodal Diffusion
- Blog: MccSTN: Multi-Scale Contrast and Fine-Grained Feature Fusion Networks for Subject-driven Style Transfer
- Blog: TextMaster: A Unified Framework for Realistic Text Editing via Glyph-Style Dual-Control
- Blog: ReFIR: Grounding Large Restoration Models with Retrieval Augmentation
- Blog: StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style Adapter
- Blog: UVMap-ID: A Controllable and Personalized UV Map Generative Model
- Blog: ATA: Adaptive Transformation Agent for Text-Guided Subject-Position Variable Background Inpainting
- Blog: BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion
- Blog: REEDIT: Multimodal Exemplar-Based Image Editing
- Blog: Moonshot: Towards Controllable Video Generation and Editing with Multimodal Conditions
- Blog: Multi-subject Open-set Personalization in Video Generation
- Blog: StoryMaker: Towards Holistic Consistent Characters in Text-to-image Generation
- Blog: RealGeneral: Unifying Visual Generation via Temporal In-Context Learning with Video Models
- Blog: Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval
- Blog: DPDEdit: Detail-Preserved Diffusion Models for Multimodal Fashion Image Editing
- Blog: Locate, Assign, Refine: Taming Customized Image Inpainting with Text-Subject Guidance
- Blog: JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation
- Blog: RomanTex: Decoupling 3D-aware Rotary Positional Embedded Multi-Attention Network for Texture Synthesis
- Blog: ArtiFade: Learning to Generate High-quality Subject from Blemished Images
- Blog: STARCaster: Spatio-Temporal AutoRegressive Video Diffusion for Identity- and View-Aware Talking Portraits
Showing 60 of 66 papers.
History & citation
Current · Permanent link
- This direction split from Decoupled Cross-Attention for Multi-Modal Diffusion (85% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_decoupled_cross_attention_e2130a9d,
title = {decoupled cross-attention},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/decoupled-cross-attention/rdr_e2130a9db9c543a0b53795b04e92a287},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 1, frozen text):
@misc{lacuna_decoupled_cross_attention_e2130a9d_v1,
title = {decoupled cross-attention},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/decoupled-cross-attention/rdr_e2130a9db9c543a0b53795b04e92a287/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-22},
}