Yu Chen
**Question 9**: Why does using a 32×32 model to generate 64×64 or 128×128 images result in distortion and more objects? **Answer**: This is due to the mismatch in model sizes....
**Question 10:** Why do I get a `RuntimeError: Address already in use` error when starting training? **Answer:** This issue often occurs when running distributed training. To resolve it, follow these...
**Question 11:** I encountered a `ValueError: Imaginary component XXX` error when calculating FID. How can I resolve it? **Answer:** The error occurs due to an excessively high version of scipy....
**Question 12:** During training, I encountered the `FutureWarning: 'torch.cuda.amp.autocast(args...)' is deprecated. Please use 'torch.amp.autocast('cuda', args...)' instead.` How should I resolve this issue? **Answer:** You can either downgrade to a Pytorch...
**Question 13**: When executing `iddm/tools/train.py` via the command line, running `python train.py` results in the error `No module 'iddm'`. How can this be resolved? **Answer**: This issue occurs due to...
这是基础的扩散模型算法，不涉及到提示词prompt的输入。 可以参考ddpm和ddim的原文，我们是根据上述论文进行复现的
12345这个地址已经被使用了，你可以在这里[修改端口](https://github.com/chairc/Integrated-Design-Diffusion-Model/blob/6b0f72ec369c212f59f769ac5315cb729a3722f1/tools/train.py#L76C13-L77C13) 
> 你好，群号加不进去。 > 可以加入啊
模型设置的输入是3通道，如果你要练灰度图可能得自己修改源代码
找到/model/networks中所有代码的`def __init__(self, in_channel=3, out_channel=3, channel=None, time_channel=256, num_classes=None, image_size=64, device="cpu", act="silu"):`，把`in_channel`和`out_channel`设置为1就行