In a few days of debugging, I basically found the training parameters and patterns of sd3.5large. This is a sample.The current progress can basically achieve 12GB graphics card memory for training SD3.5 loraIt is necessary to freeze some layers, but in reality, freezing can achieve better resultsUnder Lora's small-scale image count, training all layers with SD3.5 may cause some issues.But at relatively large image scales, all layers can be trained.The one click package of training scripts has been published on my personal media: <a target="_blank" rel="ugc" href="https://t.zsxq.com/PIme8">https://t.zsxq.com/PIme8</a>Next, we will update the frozen strategy and various training plans in personal media.The training script comes from: <a target="_blank" rel="ugc" href="https://github.com/kohya-ss/sd-scripts">https://github.com/kohya-ss/sd-scripts</a>Thank you: hhy yizhou

Files with SHA256: 687ada52d1ed4a3fba366798897c4ee4058cbb355fb7fd14df93613b3b4a1b9d