Pith. sign in

REVIEW 6 cited by

MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2304.08465 v1 pith:R2ZAVY6T submitted 2023-04-17 cs.CV

MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing

classification cs.CV
keywords editingimagegenerationconsistentmasactrlself-attentioncomplexexisting
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Despite the success in large-scale text-to-image generation and text-conditioned image editing, existing methods still struggle to produce consistent generation and editing results. For example, generation approaches usually fail to synthesize multiple images of the same objects/characters but with different views or poses. Meanwhile, existing editing methods either fail to achieve effective complex non-rigid editing while maintaining the overall textures and identity, or require time-consuming fine-tuning to capture the image-specific appearance. In this paper, we develop MasaCtrl, a tuning-free method to achieve consistent image generation and complex non-rigid image editing simultaneously. Specifically, MasaCtrl converts existing self-attention in diffusion models into mutual self-attention, so that it can query correlated local contents and textures from source images for consistency. To further alleviate the query confusion between foreground and background, we propose a mask-guided mutual self-attention strategy, where the mask can be easily extracted from the cross-attention maps. Extensive experiments show that the proposed MasaCtrl can produce impressive results in both consistent image generation and complex non-rigid real image editing.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Keep The Essentials: Efficient Reference Conditioned Generation via Token Dropping

    cs.CV 2026-06 unverdicted novelty 7.0

    Sparse Context achieves 2-4x faster inference in reference-conditioned diffusion models by fine-tuning with random token dropping and applying task-aware selection at inference time, without loss of visual quality.

  2. Semantic Browsing: Controllable Diversity for Image Generation

    cs.CV 2026-06 unverdicted novelty 7.0

    A technique for controllable diversity in text-to-image generation by inducing structured semantic variations at the prompt level via VLM and agentic workflow.

  3. ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment

    cs.CV 2024-03 unverdicted novelty 7.0

    ELLA introduces a timestep-aware semantic connector to link LLMs with diffusion models for improved dense prompt following, validated on a new 1K-prompt benchmark.

  4. Cross-Sensor SAR Data Generation Using Diffusion Models and Feature Migration

    eess.IV 2026-06 unverdicted novelty 6.0

    A diffusion-based data generation framework with attention distillation transfers sensor-specific features to synthesize training data for cross-sensor SAR applications on aircraft targets.

  5. ReAge3D: Re-Aging 3D Faces with View Consistency

    cs.CV 2026-06 unverdicted novelty 6.0

    ReAge3D trains a diffusion re-aging model on synthetic pairs then uses masked propagation from a frontal pivot view to produce consistent multi-view images that supervise 3D face optimization.

  6. InsEdit: Towards Instruction-based Visual Editing via Data-Efficient Video Diffusion Models Adaptation

    cs.CV 2026-04 unverdicted novelty 6.0

    InsEdit adapts a video diffusion backbone for text-instruction video editing via Mutual Context Attention, achieving SOTA open-source results with O(100K) data while also supporting image editing.