A multi-image diffusion stylization pipeline that averages style embeddings, fine-tunes an IPAdapter, and clusters self-attention key/value features from style images achieves state-of-the-art scores on a new style-transfer test set.
Pixart- σ: Weak-to-strong training of diffu- sion transformer for 4k text-to-image generation, 2024
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
-
Leveraging Diffusion Models for Stylization using Multiple Style Images
A multi-image diffusion stylization pipeline that averages style embeddings, fine-tunes an IPAdapter, and clusters self-attention key/value features from style images achieves state-of-the-art scores on a new style-transfer test set.