RewardFlow unifies differentiable rewards including a new VQA-based one and uses a prompt-aware adaptive policy with Langevin dynamics to achieve state-of-the-art image editing and compositional generation.
arXiv preprint arXiv:2312.04965 (2023) 18 R.Morita et al
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 5roles
background 1polarities
background 1representative citing papers
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.
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.
LimeCross enables text-guided editing of individual layers in composite images by conditioning on cross-layer context via bi-stream attention while preserving layer integrity and introducing the LayerEditBench benchmark.
citing papers explorer
-
RewardFlow: Generate Images by Optimizing What You Reward
RewardFlow unifies differentiable rewards including a new VQA-based one and uses a prompt-aware adaptive policy with Langevin dynamics to achieve state-of-the-art image editing and compositional generation.
-
Delta Rectified Flow Sampling for Text-to-Image Editing
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.
-
VAGS: Velocity Adaptive Guidance Scale for Image Editing and Generation
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.
-
LimeCross: Context-Conditioned Layered Image Editing with Structural Consistency
LimeCross enables text-guided editing of individual layers in composite images by conditioning on cross-layer context via bi-stream attention while preserving layer integrity and introducing the LayerEditBench benchmark.
- Semantic Granularity Navigation in Image Editing