indices should be either on cpu or on the same device as the indexed tensor (cpu)

[sneccc]

Every extension works fine except this one, its just the default webui code i didnt change anything

/notebooks/stable-diffusion-webui
Patching transformers to fix kwargs errors.
Dreambooth API layer loaded
Aesthetic Image Scorer: Unable to load Windows tagging script from tools directory
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
making attention of type 'vanilla' with 512 in_channels
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
making attention of type 'vanilla' with 512 in_channels
Loading weights [81761151] from /notebooks/stable-diffusion-webui/models/Stable-diffusion/v1-5-pruned-emaonly.ckpt
Global Step: 840000
Applying xformers cross attention optimization.
Model loaded.
no display name and no $DISPLAY environment variable
Loaded a total of 6 textual inversion embeddings.
Embeddings: bad_prompt_version2, gadget, testInversion, bad_prompt, testest-neg, testest
Running on local URL:  http://127.0.0.1:7860/
Running on public URL: $$$$$$$

This share link expires in 72 hours. For free permanent hosting and GPU upgrades (NEW!), check out Spaces: https://huggingface.co/spaces
Loading weights [e02601f3] from /notebooks/stable-diffusion-webui/models/Stable-diffusion/sd_v1-5_vae.ckpt
Applying xformers cross attention optimization.
Weights loaded.
Training at rate of 0.005 until step 8000
Preparing dataset...
100%|█████████████████████████████████████████████| 5/5 [00:01<00:00,  4.97it/s]
  0%|                                                  | 0/8000 [00:00<?, ?it/s]
Applying xformers cross attention optimization.
Error completing request
Arguments: ('testest', '0.005', 1, '/notebooks/kohya_ss/train_data/conceptart/', 'dream_artist', 512, 512, 8000, 500, 500, '/notebooks/stable-diffusion-webui/textual_inversion_templates/style.txt', True, False, '', '', 20, 0, 7, -1.0, 512, 512, 3.0, '', True, True, 1, 1, 1.0, 25.0, 1.0, 25.0, 0.9, 0.999, False, 1) {}
Traceback (most recent call last):
  File "/notebooks/stable-diffusion-webui/modules/ui.py", line 185, in f
    res = list(func(*args, **kwargs))
  File "/notebooks/stable-diffusion-webui/webui.py", line 57, in f
    res = func(*args, **kwargs)
  File "/notebooks/stable-diffusion-webui/extensions/DreamArtist-sd-webui-extension/scripts/dream_artist/ui.py", line 30, in train_embedding
    embedding, filename = dream_artist.cptuning.train_embedding(*args)
  File "/notebooks/stable-diffusion-webui/extensions/DreamArtist-sd-webui-extension/scripts/dream_artist/cptuning.py", line 440, in train_embedding
    output = shared.sd_model(x, c_in, scale=cfg_scale)
  File "/usr/local/lib/python3.9/dist-packages/torch/nn/modules/module.py", line 1190, in _call_impl
    return forward_call(*input, **kwargs)
  File "/notebooks/stable-diffusion-webui/repositories/stable-diffusion/ldm/models/diffusion/ddpm.py", line 879, in forward
    return self.p_losses(x, c, t, *args, **kwargs)
  File "/notebooks/stable-diffusion-webui/extensions/DreamArtist-sd-webui-extension/scripts/dream_artist/cptuning.py", line 287, in p_losses_hook
    logvar_t = self.logvar[t_raw].to(self.device)
RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)

[andykaufseo]

go to /notebooks/stable-diffusion-webui/repositories/stable-diffusion/ldm/models/diffusion/ddpm.py", line 879 and change the existing code to : logvar_t = self.logvar[t.cpu()].to(self.device)

[datacurse]

go to /notebooks/stable-diffusion-webui/repositories/stable-diffusion/ldm/models/diffusion/ddpm.py", line 879 and change the existing code to : logvar_t = self.logvar[t.cpu()].to(self.device)

Thank you, that helped! Tho i replaced line 305 of cptuning.py

[HRTK92]

Can someone please fix this bug?
https://github.com/7eu7d7/DreamArtist-sd-webui-extension/blob/fbc85703a182a32bf1db169d0fd88e5c2e3fb5a6/scripts/dream_artist/cptuning.py#L305