CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching Paper β’ 2509.19300 β’ Published 10 days ago β’ 4
DiT-Air: Revisiting the Efficiency of Diffusion Model Architecture Design in Text to Image Generation Paper β’ 2503.10618 β’ Published Mar 13 β’ 18
STIV: Scalable Text and Image Conditioned Video Generation Paper β’ 2412.07730 β’ Published Dec 10, 2024 β’ 74
Runtime error 333 333 MLLM-guided Image Editing (MGIE) π© Transform images based on textual instructions
Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models Paper β’ 2404.07973 β’ Published Apr 11, 2024 β’ 32