StyleAligned enables zero-shot style alignment in Text-to-Image (T2I) models using minimal attention sharing, ensuring consistent style transfer without fine-tuning.
generative-model
generative
depth-image
clip
canny-edge-detection
diffusion
zero-shot-learning
diffusion-models
t2i
reference-images
controlnet
style-aligned
-
Updated
Aug 31, 2024 - Jupyter Notebook