Integrated-Design-Diffusion-Model
Integrated-Design-Diffusion-Model copied to clipboard
IDDM (Industrial, landscape, animate, latent diffusion), support LDM, DDPM, DDIM, PLMS, webui and distributed training. Pytorch实现扩散模型,生成模型,分布式训练
This Issue is to summarize all kinds of problems and provide corresponding solutions. If there is no relevant problem in this issue, you can propose a new issue, and I...
When I trained 120 size images to epoch 30, **nan** appeared and all images turned black. I didn't save the model for each training, so I had to retrain my...
Version: 1.1.3 Type: BUG When I use unconditional to interrupt training, loading the model again will cause the following error. `Traceback (most recent call last): File "D:\Integrated-Design-Diffusion-Model\tools\train.py", line 408, in...
 用的ddpm,训练的参数和生成的参数都是一样的,生成出来的是噪点图,想问下是哪部分出现了问题呢
您好 首先感謝作者傑出的作品 我注意到你們conditional的條件是用類別來區分,不同於一般diffusion模型用text 且你們的模型輸入時也沒有prompt輸入 想請問你們的做法跟一般diffusion的差異 謝謝
If I do not reply in time, you can click this [issue](https://github.com/chairc/Industrial-Defect-Diffusion-Model/issues/9) to find the solution. 如果没有及时回复,可先在此[issue](https://github.com/chairc/Industrial-Defect-Diffusion-Model/issues/9)中查询
恢复训练
我在完成epoch76的时候断网了, 恢复设置为start_epoch为77, 但是开始训练的时候显示是epoch 80... 虽然不影响什么性能但也提一下吧(
请问有什么头绪吗, 谢谢大佬的解答.
作者大佬你好, 作者说40GiB显存足够训练128尺寸的图片. 请问作者团队有试过你们训练的最大可能吗? 比如256x256, 请问作者团队最大训练到多少尺寸, 用的配件条件大概是什么样的 非常感谢大佬!