ContextDrag enables precise drag-based image editing by injecting VAE-encoded reference features at aligned positions and re-encoding positional embeddings to maintain consistency in in-context models like FLUX-Kontext.
Null-text inversion for editing real images using guided diffusion models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2025 2verdicts
UNVERDICTED 2representative citing papers
RectifiedHR is a training-free method that uses noise refresh and latent energy analysis to enable efficient high-resolution synthesis in diffusion models.
citing papers explorer
-
ContextDrag: Precise Drag-Based Image Editing via Context-Preserving Token Injection and Position-Aligned Attention
ContextDrag enables precise drag-based image editing by injecting VAE-encoded reference features at aligned positions and re-encoding positional embeddings to maintain consistency in in-context models like FLUX-Kontext.
-
RectifiedHR: Enable Efficient High-Resolution Synthesis via Energy Rectification
RectifiedHR is a training-free method that uses noise refresh and latent energy analysis to enable efficient high-resolution synthesis in diffusion models.