FrankieDong


> Hello, how long did you train the model. Epoches? Iterations? Considering that train a diffusion model from scratch is very slow to converge. I set epoch 10, around 10...

> ### 🐛 Describe the bug > Hi, I tried to train stable diffusion v1 with colossal-AI, used 'train_colossalai_teyvat.yaml', but got "NotImplementedError: Some torch function is incompatible because of its...

1 error detected in the compilation of "/tmp/tmpxft_00007af2_00000000-11_cuda_util.compute_37.cpp1.ii". ninja: build stopped: subcommand failed. Traceback (most recent call last): File "/home/zrytest/diffusion/ColossalAI/colossalai/kernel/__init__.py", line 16, in from colossalai._C import multihead_attention ImportError: cannot import...

> did you install ninja? It is in requirements.txt Of course. And maybe I find the problem, I try it

> @FrankLeeeee Have you solved it? I also meet this problem. this problem occured because I don‘t pull right version from the github.

The same question for me. Maybe the epoch nums is small?

> I am trying to write simple scripts with `DiffusionPriorNetwork` and `DiffusionPrior` class, and load the pretrained model from [huggingface](https://huggingface.co/zenglishuci/conditioned-prior). > > I do the code below as the params...

you can try set strict to false, maybe is ok