A nearly training-free SDXL pipeline composes foreground content with background style using a small MLP that merges CLIP image features, removing the need for text prompts.
Kim, Zhaowen Wang, Eli Shechtman, and Trevor Darrell
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
AIComposer: Any Style and Content Image Composition via Feature Integration
A nearly training-free SDXL pipeline composes foreground content with background style using a small MLP that merges CLIP image features, removing the need for text prompts.