TenserTensor
c07827ae58
Implement Flux loading nodes: - flux_models_loader.py: basic all-in-one loader for Flux - flux_models_loader_advanced.py: extended loader with sampling shift patch, 4 LoRA slots, and advanced VAE/CLIP settings Add markdown documentation for both nodes
1.4 KiB
1.4 KiB
TT FLUX Models Loader TT_FluxModelsLoader
This description was generated with AI assistance. If you spot any errors, please create an issue on GitHub.
All-in-one model loader for Flux workflows.
Inputs
| Parameter | Type | Required | Description |
|---|---|---|---|
ckpt_name |
CHECKPOINT | Yes | Flux checkpoint to load |
clip_l |
STRING | Yes | CLIP-L text encoder model |
t5xxl |
STRING | Yes | T5-XXL text encoder model |
clip_device |
STRING | Yes | Device for CLIP ("default" or "cpu") - advanced |
vae_name |
VAE | Yes | VAE model to load |
Outputs
| Parameter | Type | Description |
|---|---|---|
MODEL |
MODEL | Loaded Flux model |
CLIP |
CLIP | Combined CLIP-L and T5-XXL text encoders |
VAE |
VAE | Loaded VAE |
Usage
Load all Flux model components in one place. Combines CLIP-L and T5-XXL encoders into a dual CLIP for Flux's text conditioning system.