Update v1.1 Freeze 30~37 layers for lora training.a simple testing lora for sd3.5Trained by T2ITrainer: <a target="_blank" rel="ugc" href="https://github.com/lrzjason/T2ITrainer">https://github.com/lrzjason/T2ITrainer</a>100 images4 rank5 repeats1 batch size2 gradient_accumulation_stepsprodigy

[SD3.5] 3DKitten

Freeze 30~37 layers for lora training.

Files with SHA256: ff9ff8cc2879eb18d19b64ccc64223fa664a5151ebf6819501478c8e6a2777ec