7 architectures. 3 training backends. 29 nodes total. 8 trainer nodes 11 selective loaders (5 V1 + 6 V2 combined) 2 analyzers (V1 + V2) 6 model layer editors 3 utility nodes This node trains LoRAs ...
Train LoRAs directly inside ComfyUI. Capture a face, a style, or a subject from your reference images and apply it to new generations - all within the same workflow. Useful for subject consistency ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback