-
### 🐛 Describe the bug
The error happens in booster.backward(loss, optimizer), I used GeminiPlugin
ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: -6) local_rank: 0 (pid: 2…
-
お忙しい中、続けてバグ案件を出して申し訳ありません。
今現在SD3.5で複数概念をうまく学習できるように色々と模索しているところではありますが、バグに遭遇したので報告させていただきます。
SD3.5で--loss_typeにsmooth_l1を指定したら、エラーが出て学習が止まりました。
以下はエラー箇所のログです。
```
D:\Lora_learning3\sd-scripts\…
-
感谢将代码开源，我看代码里有3Dunet+vae，也有3Dunet，我想使用3Dunet作为baseline看一下分割效果，loss使用自带的dice，但代码里没有直接切换网络的功能，所以我就对代码做了以下修改：
1.在config.py中把MODEL.NAME修改为unet，并且修改了data_root
2.在train_val.py中修改了训练过程：
output, vout…
-
RuntimeError: Expected is_sm80 || is_sm90 to be true, but got false. (Could this error message be improved? If so, please report an enhancement request to PyTorch.)
-
### Is there an existing issue for this?
- [X] I have searched the existing issues and checked the recent builds/commits
### What happened?
This was already discussed in another post, but it'…
-
I am trying the following code in my Docker container:
```
model = Unet(
dim = 64,
dim_mults = (1, 2, 4, 8),
flash_attn = True
)
diffusion = GaussianDif…
-
### Checklist
- [ ] The issue exists after disabling all extensions
- [X] The issue exists on a clean installation of webui
- [X] The issue is caused by an extension, but I believe it is caused by a …
-
When I load the ControlNet model I trained with diffusers, I receive an error message：safetensors_rust.SafetensorError: Error while deserializing header: MetadataIncompleteBuffer.how to solve it?
![2…
-
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: f2.0.1v1.10.1-previous-566-gcce30d33
Commit hash: cce30d3340fe7b09630a528af26975757a46c450
Launching…
-
I am trying to run AnimateDiff with ControlNet V2V. Both ControlNet and AnimateDiff work fine separately. I am following [these instructions](https://www.andyhtu.com/post/animatediff-and-controlnet-v2…