dreambooth-for-diffusion icon indicating copy to clipboard operation
dreambooth-for-diffusion copied to clipboard

AIGC模型训练工具箱 (完整封装、一体化训练stable diffusion, 可训练定制自己的独特大模型风格、人物,开箱即用,内含详细教程)

Results 8 dreambooth-for-diffusion issues
Sort by recently updated
recently updated
newest added

您好,我想用native training的方式训练新海诚风格的模型,但是我这边用了1000多张768*768分辨率的图片进行训练的,训练步数从1000到100000都有,但是发现训练的效果都很不好,文生图的结果都很鬼畜,想问下这种情况下设置的参数以及训练步数是不是设置的不对,还有是不是数据量比较少啊

该项目好像缺失LICENSE文件

RuntimeError: Error(s) in loading state_dict for AutoencoderKL: Missing key(s) in state_dict: "encoder.mid_block.attentions.0.to_q.weight", "encoder.mid_block.attentions.0.to_q.bias", "encoder.mid_block.attentions.0.to_k.weight", "encoder.mid_block.attentions.0.to_k.bias", "encoder.mid_block.attentions.0.to_v.weight", "encoder.mid_block.attentions.0.to_v.bias", "encoder.mid_block.attentions.0.to_out.0.weight", "encoder.mid_block.attentions.0.to_out.0.bias", "decoder.mid_block.attentions.0.to_q.weight", "decoder.mid_block.attentions.0.to_q.bias", "decoder.mid_block.attentions.0.to_k.weight", "decoder.mid_block.attentions.0.to_k.bias", "decoder.mid_block.attentions.0.to_v.weight", "decoder.mid_block.attentions.0.to_v.bias", "decoder.mid_block.attentions.0.to_out.0.weight", "decoder.mid_block.attentions.0.to_out.0.bias". Unexpected key(s) in...

看到有说明输入的图像需要转化为512*512维度的图像。 我有大概数千张32*32的带类别标签的图像,如何采用这些图像去重新训练stable diffusion model? 需要缩放为512*512吗?还是说有办法拿这些32*32的图像直接去训练。 如果去训练改模型,vae、unet、text encoder这些权重哪些需要改变? 我是刚入门的小白,望大佬指教

显卡是3090,微调sd1.4和sd1.5的fp32模型均没有问题,微调sd2.1的fp16和fp32模型时均显示OOM。