RevealLayer decomposes natural images into multiple RGBA layers using diffusion models with region-aware attention, occlusion-guided adaptation, and a composite loss, outperforming prior methods on a new benchmark dataset.
hub
Flowedit: Inversion-free text-based editing using pre-trained flow models
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
abstract
Editing real images using a pre-trained text-to-image (T2I) diffusion/flow model often involves inverting the image into its corresponding noise map. However, inversion by itself is typically insufficient for obtaining satisfactory results, and therefore many methods additionally intervene in the sampling process. Such methods achieve improved results but are not seamlessly transferable between model architectures. Here, we introduce FlowEdit, a text-based editing method for pre-trained T2I flow models, which is inversion-free, optimization-free and model agnostic. Our method constructs an ODE that directly maps between the source and target distributions (corresponding to the source and target text prompts) and achieves a lower transport cost than the inversion approach. This leads to state-of-the-art results, as we illustrate with Stable Diffusion 3 and FLUX. Code and examples are available on the project's webpage.
hub tools
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
VS3D performs local 3D asset editing by injecting reconstruction-anchored source signals, partial-mean guidance, and twin-agreement residuals into the velocity sampler to control edit strength and preserve identity.
FMA introduces flow matching for multi-step cross-modal feature alignment in few-shot learning, using fixed coupling, noise augmentation, and early-stopping to outperform one-step PEFT methods.
DRFS is a new inversion-free editing technique for rectified flow models that models source-target velocity discrepancies and applies a time-dependent shift to improve fidelity and unify prior methods like DDS and FlowEdit.
ICEdit achieves state-of-the-art instructional image editing in Diffusion Transformers via in-context generation, requiring only 0.1% of prior training data and 1% trainable parameters.
An end-to-end 3D editing framework achieves high-fidelity local edits from coarse bounding boxes and 2D image prompts using region-aware loss reweighting and a large-scale parts-derived training dataset.
StreamEdit enables high-quality training-free video editing by adapting streaming video generation models with dual-branch fast sampling, self-attention bridge, cross-attention grounding, source-oriented guidance, and visual prompting, outperforming prior methods in few-step regimes.
VAGS adapts the CFG scale at each ODE step using velocity alignment signals to raise structural fidelity in editing and sample quality in generation over fixed-scale baselines.
Zero-shot inversion-free flow method de-identifies skin images in under 20 seconds while preserving pathological features with IoU stability exceeding 0.67 using segment-by-synthesis and CIELAB decoupling.
A trajectory optimal control framework for reward-guided image editing in diffusion models that balances reward maximization with source fidelity better than prior inversion-based baselines.
FlashEdit delivers real-time localized text-guided image editing under 0.2 seconds via cycle-consistent one-step inversion, background shield, and sparsified spatial cross-attention, achieving over 150x speedup on PIE-Bench.
BindEdit suppresses two forms of attention leakage in diffusion-based editing by binding target tokens to regions, rebalancing cross-attention, and adding a region fidelity term, plus a new multi-object benchmark.
citing papers explorer
-
Velocity-Space 3D Asset Editing
VS3D performs local 3D asset editing by injecting reconstruction-anchored source signals, partial-mean guidance, and twin-agreement residuals into the velocity sampler to control edit strength and preserve identity.