An instruction-guided image editor that needs no training, labels, or masks: an LLM writes before/after captions and their embedding difference guides Stable Diffusion.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hands-off Image Editing: Language-guided Editing without any Task-specific Labeling, Masking or even Training
An instruction-guided image editor that needs no training, labels, or masks: an LLM writes before/after captions and their embedding difference guides Stable Diffusion.