Principle:AUTOMATIC1111 Stable diffusion webui Text Encoder Architecture
Definition
Supporting text encoder and VAE models for the SD3 pipeline.
Motivation
SD3 relies on specialized text encoder models (CLIP-L, CLIP-G, T5-XXL) and a VAE that must be defined as distinct model architectures for proper loading, weight mapping, and inference within the pipeline.
Semantic Annotations
Page Connections
Double-click a node to navigate. Hold to expand connections.
Principle
Implementation
Heuristic
Environment