Cover Image

FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image Editing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wei, Tianyi, Zhou, Yifan, Chen, Dongdong, Pan, Xingang
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Enhancing MMDiT-Based Text-to-Image Models for Similar Subject Generation
by: Wei, Tianyi, et al.
Published: (2024)

AttnRouter: Per-Category Attention Routing for Training-Free Image Editing on MMDiT
by: Li, Guandong, et al.
Published: (2026)

ReRoPE: Repurposing RoPE for Relative Camera Control
by: Li, Chunyang, et al.
Published: (2026)

E-MMDiT: Revisiting Multimodal Diffusion Transformer Design for Fast Image Synthesis under Limited Resources
by: Shen, Tong, et al.
Published: (2025)

Unraveling MMDiT Blocks: Training-free Analysis and Enhancement of Text-conditioned Diffusion
by: Li, Binglei, et al.
Published: (2026)

RoPECraft: Training-Free Motion Transfer with Trajectory-Guided RoPE Optimization on Diffusion Transformers
by: Gokmen, Ahmet Berke, et al.
Published: (2025)

Anchor Forcing: Anchor Memory and Tri-Region RoPE for Interactive Streaming Video Diffusion
by: Yang, Yang, et al.
Published: (2026)

Untwisting RoPE: Frequency Control for Shared Attention in DiTs
by: Mikaeili, Aryan, et al.
Published: (2026)

A Circular Argument : Does RoPE need to be Equivariant for Vision?
by: van de Geijn, Chase, et al.
Published: (2025)

Demystifying the Slash Pattern in Attention: The Role of RoPE
by: Cheng, Yuan, et al.
Published: (2026)

Spiral RoPE: Rotate Your Rotary Positional Embeddings in the 2D Plane
by: Liu, Haoyu, et al.
Published: (2026)

Base of RoPE Bounds Context Length
by: Men, Xin, et al.
Published: (2024)

RoPE-LIME: RoPE-Space Locality + Sparse-K Sampling for Efficient LLM Attribution
by: Picov, Isaac, et al.
Published: (2026)

Diffusion MRI Transformer with a Diffusion Space Rotary Positional Embedding (D-RoPE)
by: Kung, Gustavo Chau Loo, et al.
Published: (2026)

ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models
by: Yan, Feihong, et al.
Published: (2026)

RoPeSLR: 3D RoPE-driven Sparse-LowRank Attention for Efficient Diffusion Transformers
by: Liu, Yuxi, et al.
Published: (2026)

Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout
by: Yesiltepe, Hidir, et al.
Published: (2025)

Understanding the RoPE Extensions of Long-Context LLMs: An Attention Perspective
by: Zhong, Meizhi, et al.
Published: (2024)

Periodic RoPE for Infinite Context LLMs
by: Huo, Simin
Published: (2026)

Scaling Laws of RoPE-based Extrapolation
by: Liu, Xiaoran, et al.
Published: (2023)

ID-Align: RoPE-Conscious Position Remapping for Dynamic High-Resolution Adaptation in Vision-Language Models
by: Li, Bozhou, et al.
Published: (2025)

Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models
by: Fortes, Armando, et al.
Published: (2025)

CoPE: Clipped RoPE as A Scalable Free Lunch for Long Context LLMs
by: Li, Haoran, et al.
Published: (2026)

Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers
by: Zhou, Yifan, et al.
Published: (2025)

On the token distance modeling ability of higher RoPE attention dimension
by: Hong, Xiangyu, et al.
Published: (2024)

Rotate Both Ways: Time-and-Order RoPE for Generative Recommendation
by: Wei, Xiaokai, et al.
Published: (2025)

RoPE Attention Can Be Trained in Almost Linear Time
by: Cao, Yang, et al.
Published: (2024)

Frayed RoPE and Long Inputs: A Geometric Perspective
by: Wertheimer, Davis, et al.
Published: (2026)

Circuit Complexity Bounds for RoPE-based Transformer Architecture
by: Chen, Bo, et al.
Published: (2024)

Alias-Free Latent Diffusion Models: Improving Fractional Shift Equivariance of Diffusion Latent Space
by: Zhou, Yifan, et al.
Published: (2025)

RoSA: Enhancing Parameter-Efficient Fine-Tuning via RoPE-aware Selective Adaptation in Large Language Models
by: Pan, Dayan, et al.
Published: (2025)

Rethinking RoPE: A Mathematical Blueprint for N-dimensional Positional Embedding
by: Liu, Haiping, et al.
Published: (2025)

MvDrag3D: Drag-based Creative 3D Editing via Multi-view Generation-Reconstruction Priors
by: Chen, Honghua, et al.
Published: (2024)

RAP: KV-Cache Compression via RoPE-Aligned Pruning
by: Xin, Jihao, et al.
Published: (2026)

LinearARD: Linear-Memory Attention Distillation for RoPE Restoration
by: Yang, Ning, et al.
Published: (2026)

Resonance RoPE: Improving Context Length Generalization of Large Language Models
by: Wang, Suyuchen, et al.
Published: (2024)

Fast RoPE Attention: Combining the Polynomial Method and Fast Fourier Transform
by: Alman, Josh, et al.
Published: (2025)

Shuffle the Context: RoPE-Perturbed Self-Distillation for Long-Context Adaptation
by: Li, Zichong, et al.
Published: (2026)

Fractional Rotation, Full Potential? Investigating Performance and Convergence of Partial RoPE
by: Khan, Mohammad Aflah, et al.
Published: (2026)

RoPE Distinguishes Neither Positions Nor Tokens in Long Contexts, Provably
by: Du, Yufeng, et al.
Published: (2026)