可参考:https://github.com/Stability-AI/StableCascade/tree/master/inference LoRA 官方还提供了LoRA 训练和使用Stable Cascade的实现,可以用于微调文本条件模型(Stage C)。具体来说可以添加和学习新的标注,并向模型添加 LoRA 层。LoRA文档展示了如何使用训练好的 LoRA。例如,对狗进行训练的 LoRA,使用以下类型的训练...
model is well suited for usages where efficiency is important. Furthermore, all known extensions like finetuning, LoRA, ControlNet, IP-Adapter, LCM etc. are possible with this method as well. A few of those are already provided (finetuning, ControlNet, LoRA) in thetrainingandinferencesections...
我有一个黑客朋友,他做了一个APP叫做 Draw Things,应该是我知道的第一个把 Stable Diffusion 成功编译到手机上的一个应用。你可以在 iOS 平台上下载到它,用手机做inference(推理)。实际上这是很难的,因为哪怕是台很好的台式机,做inference 也是很费劲的。但是它是最早一批成功在手机上编译并且成功运行inference ...
model is well suited for usages where efficiency is important. Furthermore, all known extensions like finetuning, LoRA, ControlNet, IP-Adapter, LCM etc. are possible with this method as well. A few of those are already provided (finetuning, ControlNet, LoRA) in thetrainingandinferencesections...