Nodes3 min read
IPAdapter Plus reference: presets, vision encoders and FaceID dependenciesPinned source defines IPAdapterUnifiedLoader as a MODEL and preset loader that returns MODEL plus IPADAPTER; the reference image enters a later apply node.
THE LIBRARY / NODES
Nodes
Published references, source identities and connected reading.
Nodes3 min read
VideoHelperSuite reference: frame loading, audio, composition and saved outputVHS_VideoCombine illustrates the media layer around generated content. Reading, sampling frames, combining and saving should not be confused with the generation model itself.
Nodes2 min read
TextEncodeQwenImage21: reference inputs, resolution and latent outputDocument the core class and its input/output contract without confusing UI capacity with model support.
Base model
- Qwen-Image 2.1
Nodes2 min read
QwenImage21Cache: cache placement is not weight quantizationUnderstand cache placement and storage precision as separate controls from model-file quantization.
Base model
- Qwen-Image 2.1