FLUX.1 Kontext unifies image generation and editing via flow matching and sequence concatenation, delivering improved multi-turn consistency and speed on the new KontextBench benchmark.
Magicbrush: A manually annotated dataset for instruction-guided image editing.ArXiv, abs/2306.10012
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
dataset 1
citation-polarity summary
verdicts
UNVERDICTED 5representative citing papers
SEED-X is a unified multimodal foundation model that handles multi-granularity visual semantics for both comprehension and generation across arbitrary image sizes and ratios.
Edit-GRPO decouples editing and preservation objectives via region-specific signals in a policy optimization framework to improve locality in image editing tasks.
Sequential decomposition trained on synthetic editing tasks improves robustness for complex image instructions and transfers to real images via co-training.
This review organizes literature on large multimodal models and object-centric vision into four themes—understanding, referring segmentation, editing, and generation—while summarizing paradigms, strategies, and challenges like instance permanence and consistent interaction.
citing papers explorer
-
FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
FLUX.1 Kontext unifies image generation and editing via flow matching and sequence concatenation, delivering improved multi-turn consistency and speed on the new KontextBench benchmark.
-
SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation
SEED-X is a unified multimodal foundation model that handles multi-granularity visual semantics for both comprehension and generation across arbitrary image sizes and ratios.
-
Edit-GRPO: A Locality-Preserving Policy Optimization Framework for Image Editing
Edit-GRPO decouples editing and preservation objectives via region-specific signals in a policy optimization framework to improve locality in image editing tasks.
-
Towards Robust Sequential Decomposition for Complex Image Editing
Sequential decomposition trained on synthetic editing tasks improves robustness for complex image instructions and transfers to real images via co-training.
-
LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation
This review organizes literature on large multimodal models and object-centric vision into four themes—understanding, referring segmentation, editing, and generation—while summarizing paradigms, strategies, and challenges like instance permanence and consistent interaction.