Insert Anything is a single model fine-tuned on 159,908 prompt-image pairs that performs mask- or text-guided insertion of people, objects, and garments from reference images into target scenes.
Anydoor: Zero-shot object-level im- age customization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Insert Anything: Image Insertion via In-Context Editing in DiT
Insert Anything is a single model fine-tuned on 159,908 prompt-image pairs that performs mask- or text-guided insertion of people, objects, and garments from reference images into target scenes.