Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
EasyOCR
Findings
IC-394
Text generation in SDXL, DeepFloyd IF, and SD3 is controlled by less than 1% of parameters concentrated in specific cross- or joint-attention layers, and these layers are specialised for text content rather than visual template
[eval]