SOTAVerified

Text-based Image Editing

Nose should be sharped and lips should be less fat

Papers

Showing 1–10 of 45 papers

TitleStatusHype
NoHumansRequired: Autonomous High-Quality Image Editing Triplet Mining—0
Cora: Correspondence-aware image editing using few step diffusionCode1
POEM: Precise Object-level Editing via MLLM control—0
ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion RefinementCode2
KV-Edit: Training-Free Image Editing for Precise Background PreservationCode3
PartEdit: Fine-Grained Image Editing using Pre-Trained Diffusion Models—0
FeedEdit: Text-Based Image Editing with Dynamic Feedback Regulation—0
FireFlow: Fast Inversion of Rectified Flow for Image Semantic EditingCode3
Action-based image editing guided by human instructions—0
LoRA of Change: Learning to Generate LoRA for the Editing Instruction from A Single Before-After Image Pair—0
Show:102550
← PrevPage 1 of 5Next →

No leaderboard results yet.