[Bug]: Missing model directory, removing model

[alesys]

Is there an existing issue for this?

• [X] I have searched the existing issues and checked the recent builds/commits of both this extension and the webui

What happened?

After this last update it is not possible to do Model / Create / Create Model.

Steps to reproduce the problem

Update to the latest version. Go to Dreambooth tab. Attempt to create a new Model.

Commit and libraries

Initializing Dreambooth Dreambooth revision: b4053defa6ae018b2ea56ac243aa55063f76fe0e Successfully installed accelerate-0.21.0 diffusers-0.19.3 fastapi-0.94.1 gitpython-3.1.32 transformers-4.30.2

Does your project take forever to startup? Repetitive dependency installation may be the reason. Automatic1111's base project sets strict requirements on outdated dependencies. If an extension is using a newer version, the dependency is uninstalled and reinstalled twice every startup.

[+] xformers version 0.0.20 installed. [+] torch version 2.0.1+cu118 installed. [+] torchvision version 0.15.2+cu118 installed. [+] accelerate version 0.21.0 installed. [+] diffusers version 0.19.3 installed. [+] transformers version 4.30.2 installed. [+] bitsandbytes version 0.35.4 installed.

Command Line Arguments

No

Console logs

https://pastebin.com/TkdechPQ

Additional information

No response

[maciegg]

I have the same problem

[maciegg]

For me worked this fix https://github.com/d8ahazard/sd_dreambooth_extension/issues/1290

[jmaccall316]

Can confirm the same issue. I got it to work by adding parts of the diffusion model manually. When creating model it will only convert unet and scheduler, but stops at vae giving above issue. To get it to work i had to add the folder/subfolder in models/dreambooth = " tty/working", then add model_index.json, vae, text_encoder, feature_extractor and tokenizer folders and contents myself, then create the model again "tty"

[AlexMcCown]

I had this same issue, i had to change line 1278 in sd_to_diff.py from vae.load_state_dict(converted_vae_checkpoint) to vae.load_state_dict(converted_vae_checkpoint, strict=False) However as a result i have had some model issues, i have had to start up with --disable-nan-check to get txt2img to work and img2img no longer works on the trained model so i would not call this a fix; however it does in a pinch

[mcgrimm]

same issue above just fyi , i think my turnarround solution is try reinstall other version streambooth by

git checkout https://github.com/d8ahazard/sd_dreambooth_extension/commit/dc413a14379b165355502d9f65856c40a4bb5b6f

then pip install -r requirments.txt underneath the dreambooth folder.

[github-actions[bot]]

This issue is stale because it has been open 5 days with no activity. Remove stale label or comment or this will be closed in 5 days

[desper327]

可以确认同样的问题。我通过手动添加扩散模型的部分来使其工作。创建模型时，它只会转换unet和调度程序，但会在给出上述问题的vae处停止。为了让它工作，我必须在 models/dreambooth = " tty/working" 中添加文件夹/子文件夹，然后添加 model_index.json、vae、text_encoder、feature_extractor 和 tokenizer 文件夹和内容，然后再次创建模型“tty”

It's really worked for me ,thank you !