SOTAVerified

Personalized Image Generation

Utilizes single or multiple images that contain the same subject or style, along with text prompt, to generate images that contain that subject as well as match the textual description. Includes finetuning-based methods (e.g. DreamBooth, Textual Inversion) as well as encoder-based methods (e.g. E4T, ELITE, and IP-Adapter, etc.).

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 58 papers

TitleStatusHype
A Training-Free Style-Personalization via Scale-wise Autoregressive Model—0
RAGAR: Retrieval Augment Personalized Image Generation Guided by Recommendation—0
DRC: Enhancing Personalized Image Generation via Disentangled Representation Composition—0
Personalized Text-to-Image Generation with Auto-Regressive ModelsCode1
AC-LoRA: Auto Component LoRA for Personalized Artistic Style Image Generation—0
Less-to-More Generalization: Unlocking More Controllability by In-Context GenerationCode5
Personalize Anything for Free with Diffusion Transformer—0
Conceptrol: Concept Control of Zero-shot Personalized Image GenerationCode1
Towards More Accurate Personalized Image Generation: Addressing Overfitting and Evaluation BiasCode0
Personalized Image Generation with Deep Generative Models: A Decade SurveyCode3
Beyond Fine-Tuning: A Systematic Study of Sampling Techniques in Personalized Image GenerationCode1
A4A: Adapter for Adapter Transfer via All-for-All Mapping for Cross-Architecture Models—0
HyperNet Fields: Efficiently Training Hypernetworks without Ground Truth by Learning Weight Trajectories—0
PersonaMagic: Stage-Regulated High-Fidelity Face Customization with Tandem EquilibriumCode1
LoRACLR: Contrastive Adaptation for Customization of Diffusion Models—0
PatchDPO: Patch-level DPO for Finetuning-free Personalized Image GenerationCode1
SerialGen: Personalized Image Generation by First Standardization Then Personalization—0
DreamBlend: Advancing Personalized Fine-tuning of Text-to-Image Diffusion Models—0
PersonaCraft: Personalized Full-Body Image Synthesis for Multiple Identities from Single References Using 3D-Model-Conditioned Diffusion—0
DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching—0
Personalized Image Generation with Large Multimodal ModelsCode1
FaceChain-FACT: Face Adapter with Decoupled Training for Identity-preserved PersonalizationCode0
Resolving Multi-Condition Confusion for Finetuning-Free Personalized Image GenerationCode2
Imagine yourself: Tuning-Free Personalized Image Generation—0
StoryMaker: Towards Holistic Consistent Characters in Text-to-image GenerationCode4
Show:102550
← PrevPage 1 of 3Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DreamBooth LoRA SDXL v1.0Overall (CP * PF)0.52—Unverified
2IP-Adapter ViT-G SDXL v1.0Overall (CP * PF)0.38—Unverified
3Emu2 SDXL v1.0Overall (CP * PF)0.36—Unverified
4DreamBooth SD v1.5Overall (CP * PF)0.36—Unverified
5IP-Adapter-Plus ViT-H SDXL v1.0Overall (CP * PF)0.34—Unverified
6BLIP-Diffusion SD v1.5Overall (CP * PF)0.27—Unverified
7Textual Inversion SD v1.5Overall (CP * PF)0.24—Unverified