Compose and Conquer: Diffusion-Based 3D Depth Aware Composable Image Synthesis
Paper
•
2401.09048
•
Published
•
9
image
-
-
Improving fine-grained understanding in image-text pre-training
Paper • 2401.09865 • Published • 16 -
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
Paper • 2401.10891 • Published • 59 -
Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild
Paper • 2401.13627 • Published • 73 -
UNIMO-G: Unified Image Generation through Multimodal Conditional Diffusion
Paper • 2401.13388 • Published • 11 -
DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editing
Paper • 2402.02583 • Published • 7 -
SDXL-Lightning: Progressive Adversarial Diffusion Distillation
Paper • 2402.13929 • Published • 28 -
T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching
Paper • 2402.14167 • Published • 10 -
Subobject-level Image Tokenization
Paper • 2402.14327 • Published • 17 -
Gen4Gen: Generative Data Pipeline for Generative Multi-Concept Composition
Paper • 2402.15504 • Published • 21 -
Multi-LoRA Composition for Image Generation
Paper • 2402.16843 • Published • 28 -
EMO: Emote Portrait Alive - Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions
Paper • 2402.17485 • Published • 189 -
DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
Paper • 2402.19481 • Published • 20 -
Trajectory Consistency Distillation
Paper • 2402.19159 • Published • 14 -
RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization
Paper • 2403.00483 • Published • 12 -
ResAdapter: Domain Consistent Resolution Adapter for Diffusion Models
Paper • 2403.02084 • Published • 14 -
OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on
Paper • 2403.01779 • Published • 28 -
Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
Paper • 2403.03206 • Published • 59 -
ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
Paper • 2403.05135 • Published • 42 -
Motion Mamba: Efficient and Long Sequence Motion Generation with Hierarchical and Bidirectional Selective SSM
Paper • 2403.07487 • Published • 13 -
Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering
Paper • 2403.09622 • Published • 16 -
StreamMultiDiffusion: Real-Time Interactive Generation with Region-Based Semantic Control
Paper • 2403.09055 • Published • 24 -
IDAdapter: Learning Mixed Features for Tuning-Free Personalization of Text-to-Image Models
Paper • 2403.13535 • Published • 22 -
DepthFM: Fast Monocular Depth Estimation with Flow Matching
Paper • 2403.13788 • Published • 17 -
Magic Fixup: Streamlining Photo Editing by Watching Dynamic Videos
Paper • 2403.13044 • Published • 15 -
FlashFace: Human Image Personalization with High-fidelity Identity Preservation
Paper • 2403.17008 • Published • 19 -
SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions
Paper • 2403.16627 • Published • 20 -
ViTAR: Vision Transformer with Any Resolution
Paper • 2403.18361 • Published • 52 -
ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertion
Paper • 2403.18818 • Published • 25 -
CosmicMan: A Text-to-Image Foundation Model for Humans
Paper • 2404.01294 • Published • 15 -
Condition-Aware Neural Network for Controlled Image Generation
Paper • 2404.01143 • Published • 11 -
Measuring Style Similarity in Diffusion Models
Paper • 2404.01292 • Published • 16 -
CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching
Paper • 2404.03653 • Published • 33 -
RL for Consistency Models: Faster Reward Guided Text-to-Image Generation
Paper • 2404.03673 • Published • 14 -
ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback
Paper • 2404.07987 • Published • 47 -
Scaling (Down) CLIP: A Comprehensive Analysis of Data, Architecture, and Training Strategies
Paper • 2404.08197 • Published • 27 -
Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model
Paper • 2404.09967 • Published • 20 -
HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing
Paper • 2404.09990 • Published • 12 -
Dynamic Typography: Bringing Words to Life
Paper • 2404.11614 • Published • 44 -
MoA: Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation
Paper • 2404.11565 • Published • 14 -
Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis
Paper • 2404.13686 • Published • 27 -
Align Your Steps: Optimizing Sampling Schedules in Diffusion Models
Paper • 2404.14507 • Published • 21 -
PuLID: Pure and Lightning ID Customization via Contrastive Alignment
Paper • 2404.16022 • Published • 21 -
Editable Image Elements for Controllable Synthesis
Paper • 2404.16029 • Published • 10 -
ID-Aligner: Enhancing Identity-Preserving Text-to-Image Generation with Reward Feedback Learning
Paper • 2404.15449 • Published • 11 -
ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving
Paper • 2404.16771 • Published • 16 -
StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation
Paper • 2405.01434 • Published • 52 -
Customizing Text-to-Image Models with a Single Image Pair
Paper • 2405.01536 • Published • 18 -
Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Control
Paper • 2405.12970 • Published • 22 -
RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance
Paper • 2405.14677 • Published • 9 -
DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis
Paper • 2405.14224 • Published • 12 -
Semantica: An Adaptable Image-Conditioned Diffusion Model
Paper • 2405.14857 • Published • 8 -
EM Distillation for One-step Diffusion Models
Paper • 2405.16852 • Published • 10 -
Greedy Growing Enables High-Resolution Pixel-Based Diffusion Models
Paper • 2405.16759 • Published • 7 -
Phased Consistency Model
Paper • 2405.18407 • Published • 46 -
BitsFusion: 1.99 bits Weight Quantization of Diffusion Model
Paper • 2406.04333 • Published • 36 -
pOps: Photo-Inspired Diffusion Operators
Paper • 2406.01300 • Published • 16 -
Zero-shot Image Editing with Reference Imitation
Paper • 2406.07547 • Published • 31 -
An Image is Worth 32 Tokens for Reconstruction and Generation
Paper • 2406.07550 • Published • 55 -
AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising
Paper • 2406.06911 • Published • 10 -
FontStudio: Shape-Adaptive Diffusion Model for Coherent and Consistent Font Effect Generation
Paper • 2406.08392 • Published • 18 -
Depth Anything V2
Paper • 2406.09414 • Published • 92 -
An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels
Paper • 2406.09415 • Published • 50 -
Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models
Paper • 2406.09416 • Published • 28 -
EMMA: Your Text-to-Image Diffusion Model Can Secretly Accept Multi-Modal Prompts
Paper • 2406.09162 • Published • 13 -
Glyph-ByT5-v2: A Strong Aesthetic Baseline for Accurate Multilingual Visual Text Rendering
Paper • 2406.10208 • Published • 21 -
Exploring the Role of Large Language Models in Prompt Encoding for Diffusion Models
Paper • 2406.11831 • Published • 20 -
The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing
Paper • 2406.10601 • Published • 65 -
Invertible Consistency Distillation for Text-Guided Image Editing in Around 7 Steps
Paper • 2406.14539 • Published • 26 -
DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation
Paper • 2406.16855 • Published • 54 -
Aligning Diffusion Models with Noise-Conditioned Perception
Paper • 2406.17636 • Published • 26 -
Magic Insert: Style-Aware Drag-and-Drop
Paper • 2407.02489 • Published • 20 -
DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents
Paper • 2407.03300 • Published • 11 -
PartCraft: Crafting Creative Objects by Parts
Paper • 2407.04604 • Published • 4 -
SVGCraft: Beyond Single Object Text-to-SVG Synthesis with Comprehensive Canvas Layout
Paper • 2404.00412 • Published • 2 -
DataDream: Few-shot Guided Dataset Generation
Paper • 2407.10910 • Published • 8 -
Scaling Diffusion Transformers to 16 Billion Parameters
Paper • 2407.11633 • Published • 25 -
IMAGDressing-v1: Customizable Virtual Dressing
Paper • 2407.12705 • Published • 12 -
CGB-DM: Content and Graphic Balance Layout Generation with Transformer-based Diffusion Model
Paper • 2407.15233 • Published • 6 -
Artist: Aesthetically Controllable Text-Driven Stylization without Training
Paper • 2407.15842 • Published • 13 -
Discrete Flow Matching
Paper • 2407.15595 • Published • 11 -
ViPer: Visual Personalization of Generative Models via Individual Preference Learning
Paper • 2407.17365 • Published • 11 -
Diffree: Text-Guided Shape Free Object Inpainting with Diffusion Model
Paper • 2407.16982 • Published • 40 -
BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation
Paper • 2407.17952 • Published • 29 -
SHIC: Shape-Image Correspondences with no Keypoint Supervision
Paper • 2407.18907 • Published • 40 -
TurboEdit: Text-Based Image Editing Using Few-Step Diffusion Models
Paper • 2408.00735 • Published • 15 -
Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention
Paper • 2408.00760 • Published • 6 -
Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining
Paper • 2408.02657 • Published • 32 -
ProCreate, Dont Reproduce! Propulsive Energy Diffusion for Creative Generation
Paper • 2408.02226 • Published • 10 -
IPAdapter-Instruct: Resolving Ambiguity in Image-based Conditioning using Instruct Prompts
Paper • 2408.03209 • Published • 21 -
Openstory++: A Large-scale Dataset and Benchmark for Instance-aware Open-domain Visual Storytelling
Paper • 2408.03695 • Published • 12 -
ControlNeXt: Powerful and Efficient Control for Image and Video Generation
Paper • 2408.06070 • Published • 52 -
BRAT: Bonus oRthogonAl Token for Architecture Agnostic Textual Inversion
Paper • 2408.04785 • Published • 6 -
UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalization
Paper • 2408.05939 • Published • 13 -
Imagen 3
Paper • 2408.07009 • Published • 61 -
ZePo: Zero-Shot Portrait Stylization with Faster Sampling
Paper • 2408.05492 • Published • 7 -
Generative Photomontage
Paper • 2408.07116 • Published • 19 -
JPEG-LM: LLMs as Image Generators with Canonical Codec Representations
Paper • 2408.08459 • Published • 44 -
TurboEdit: Instant text-based image editing
Paper • 2408.08332 • Published • 19 -
Photorealistic Object Insertion with Diffusion-Guided Inverse Rendering
Paper • 2408.09702 • Published • 9 -
TraDiffusion: Trajectory-Based Training-Free Image Generation
Paper • 2408.09739 • Published • 8 -
MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuning
Paper • 2408.11001 • Published • 11 -
The Brittleness of AI-Generated Image Watermarking Techniques: Examining Their Robustness Against Visual Paraphrasing Attacks
Paper • 2408.10446 • Published • 6 -
Scalable Autoregressive Image Generation with Mamba
Paper • 2408.12245 • Published • 25 -
CODE: Confident Ordinary Differential Editing
Paper • 2408.12418 • Published • 4 -
SwiftBrush v2: Make Your One-step Diffusion Model Better Than Its Teacher
Paper • 2408.14176 • Published • 60 -
Build-A-Scene: Interactive 3D Layout Control for Diffusion-Based Image Generation
Paper • 2408.14819 • Published • 20 -
Distribution Backtracking Builds A Faster Convergence Trajectory for One-step Diffusion Distillation
Paper • 2408.15991 • Published • 15 -
CSGO: Content-Style Composition in Text-to-Image Generation
Paper • 2408.16766 • Published • 17 -
CoRe: Context-Regularized Text Embedding Learning for Text-to-Image Personalization
Paper • 2408.15914 • Published • 22 -
VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers
Paper • 2408.17131 • Published • 11 -
LinFusion: 1 GPU, 1 Minute, 16K Image
Paper • 2409.02097 • Published • 32 -
Accurate Compression of Text-to-Image Diffusion Models via Vector Quantization
Paper • 2409.00492 • Published • 11 -
Guide-and-Rescale: Self-Guidance Mechanism for Effective Tuning-Free Real Image Editing
Paper • 2409.01322 • Published • 94 -
IFAdapter: Instance Feature Control for Grounded Text-to-Image Generation
Paper • 2409.08240 • Published • 18 -
InstantDrag: Improving Interactivity in Drag-based Image Editing
Paper • 2409.08857 • Published • 30 -
StoryMaker: Towards Holistic Consistent Characters in Text-to-image Generation
Paper • 2409.12576 • Published • 15 -
Imagine yourself: Tuning-Free Personalized Image Generation
Paper • 2409.13346 • Published • 67 -
Colorful Diffuse Intrinsic Image Decomposition in the Wild
Paper • 2409.13690 • Published • 12 -
Improvements to SDXL in NovelAI Diffusion V3
Paper • 2409.15997 • Published • 11 -
Pixel-Space Post-Training of Latent Diffusion Models
Paper • 2409.17565 • Published • 19 -
OmniBooth: Learning Latent Control for Image Synthesis with Multi-modal Instruction
Paper • 2410.04932 • Published • 9 -
Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding
Paper • 2410.01699 • Published • 18 -
IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation
Paper • 2410.07171 • Published • 41 -
Story-Adapter: A Training-free Iterative Framework for Long Story Visualization
Paper • 2410.06244 • Published • 19 -
Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models
Paper • 2410.02416 • Published • 25 -
DICE: Discrete Inversion Enabling Controllable Editing for Multinomial Diffusion and Masked Generative Models
Paper • 2410.08207 • Published • 18 -
Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis
Paper • 2410.08261 • Published • 49 -
EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models
Paper • 2410.07133 • Published • 18 -
Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations
Paper • 2410.10792 • Published • 26 -
Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices
Paper • 2410.11795 • Published • 16 -
Improving Long-Text Alignment for Text-to-Image Diffusion Models
Paper • 2410.11817 • Published • 14 -
Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens
Paper • 2410.13863 • Published • 35 -
VidPanos: Generative Panoramic Videos from Casual Panning Videos
Paper • 2410.13832 • Published • 12 -
FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model
Paper • 2410.13925 • Published • 22 -
BiGR: Harnessing Binary Latent Codes for Image Generation and Improved Visual Representation Capabilities
Paper • 2410.14672 • Published • 7 -
Scalable Ranked Preference Optimization for Text-to-Image Generation
Paper • 2410.18013 • Published • 14 -
Stable Consistency Tuning: Understanding and Improving Consistency Models
Paper • 2410.18958 • Published • 9 -
DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation
Paper • 2410.18666 • Published • 18 -
Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse Autoencoders
Paper • 2410.22366 • Published • 75 -
Constant Acceleration Flow
Paper • 2411.00322 • Published • 23 -
In-Context LoRA for Diffusion Transformers
Paper • 2410.23775 • Published • 10 -
Training-free Regional Prompting for Diffusion Transformers
Paper • 2411.02395 • Published • 25 -
Constrained Diffusion Implicit Models
Paper • 2411.00359 • Published • 6 -
SVDQunat: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
Paper • 2411.05007 • Published • 16 -
Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models
Paper • 2411.07232 • Published • 62 -
OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision
Paper • 2411.07199 • Published • 44 -
Edify Image: High-Quality Image Generation with Pixel Space Laplacian Diffusion Models
Paper • 2411.07126 • Published • 28 -
Watermark Anything with Localized Messages
Paper • 2411.07231 • Published • 20 -
JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation
Paper • 2411.07975 • Published • 26 -
Scaling Properties of Diffusion Models for Perceptual Tasks
Paper • 2411.08034 • Published • 13 -
MagicQuill: An Intelligent Interactive Image Editing System
Paper • 2411.09703 • Published • 56 -
Inconsistencies In Consistency Models: Better ODE Solving Does Not Imply Better Samples
Paper • 2411.08954 • Published • 6 -
Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement
Paper • 2411.06558 • Published • 34 -
FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on
Paper • 2411.10499 • Published • 13 -
Continuous Speculative Decoding for Autoregressive Image Generation
Paper • 2411.11925 • Published • 14 -
Stylecodes: Encoding Stylistic Information For Image Generation
Paper • 2411.12811 • Published • 10 -
Generating Compositional Scenes via Text-to-image RGBA Instance Generation
Paper • 2411.10913 • Published • 3 -
Stable Flow: Vital Layers for Training-Free Image Editing
Paper • 2411.14430 • Published • 13 -
Style-Friendly SNR Sampler for Style-Driven Generation
Paper • 2411.14793 • Published • 35 -
OminiControl: Minimal and Universal Control for Diffusion Transformer
Paper • 2411.15098 • Published • 39 -
MyTimeMachine: Personalized Facial Age Transformation
Paper • 2411.14521 • Published • 15 -
Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generator
Paper • 2411.15466 • Published • 33 -
One Diffusion to Generate Them All
Paper • 2411.16318 • Published • 23 -
Controllable Human Image Generation with Personalized Multi-Garments
Paper • 2411.16801 • Published • 3 -
ROICtrl: Boosting Instance Control for Visual Generation
Paper • 2411.17949 • Published • 72 -
DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching
Paper • 2411.17786 • Published • 9 -
Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient
Paper • 2411.17787 • Published • 11