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
Less-to-More Generalization: Unlocking More Controllability by In-Context GenerationCode5
DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven GenerationCode5
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual InversionCode5
IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion ModelsCode5
StoryMaker: Towards Holistic Consistent Characters in Text-to-image GenerationCode4
Generative Multimodal Models are In-Context LearnersCode3
MoMA: Multimodal LLM Adapter for Fast Personalized Image GenerationCode3
Personalized Image Generation with Deep Generative Models: A Decade SurveyCode3
Subject-Diffusion:Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuningCode2
DreamBench++: A Human-Aligned Benchmark for Personalized Image GenerationCode2
Gen4Gen: Generative Data Pipeline for Generative Multi-Concept CompositionCode2
When StyleGAN Meets Stable Diffusion: a W+ Adapter for Personalized Image GenerationCode2
TextBoost: Towards One-Shot Personalization of Text-to-Image Models via Fine-tuning Text EncoderCode2
RectifID: Personalizing Rectified Flow with Anchored Classifier GuidanceCode2
FastComposer: Tuning-Free Multi-Subject Image Generation with Localized AttentionCode2
Resolving Multi-Condition Confusion for Finetuning-Free Personalized Image GenerationCode2
EZIGen: Enhancing zero-shot personalized image generation with precise subject encoding and decoupled guidanceCode2
BootPIG: Bootstrapping Zero-shot Personalized Image Generation Capabilities in Pretrained Diffusion ModelsCode1
PersonaMagic: Stage-Regulated High-Fidelity Face Customization with Tandem EquilibriumCode1
Personalized Image Generation with Large Multimodal ModelsCode1
Personalized Text-to-Image Generation with Auto-Regressive ModelsCode1
When StyleGAN Meets Stable Diffusion: a W_+ Adapter for Personalized Image GenerationCode1
Beyond Fine-Tuning: A Systematic Study of Sampling Techniques in Personalized Image GenerationCode1
Conceptrol: Concept Control of Zero-shot Personalized Image GenerationCode1
PatchDPO: Patch-level DPO for Finetuning-free Personalized Image GenerationCode1
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