linaqruf / vladmandic-webui-colab Goto Github PK

1. CN Tile model "control_v11u__sd15_tile" is obsolete. Can you please update it to "control_v11f1e__sd15_tile"?
2. I tried to start ngrok tunnel and got an error about cloudflare. I did everything right - chose ngrok option and paste my ngrok token. So I deleted this line and started the cell again. It worked just fine without that line.
   

Hey man I think there are some errors since the new update. Cannot launch SD

Links to Ngrok and Gradio are broken. The last block loads the model and gives a link, but it doesn't work.

Custom Download Corner does not download models. Embedding and Lora don't save the file format, or make it .1

https://huggingface.co/comfyanonymous/ControlNet-v1-1_fp16_safetensors/resolve/main/control_v11f1e_sd15_tile_fp16.safetensors

Hello, SD.Next recent implementation of diffusers is really interesting and many people don't have the GPU for it.
Could you please update this notebook so that it works with recent SD.Next as well as add all the good stuff you added to the auto1111 one ? Eventually we could add a link to run updated notebook with collab.

Have a good day

Hi!

The recent kohya trainer errors can be found in this repo as well. I tried to fix it myself, but failed. I managed to get models to download, but then the tcmalloc issue happened as well.

Thank you!

Worked yesterday. On uploading an image to inpaint, the image is blank. Works on the imgtoimg tab but not on the inpaint tab.

Error popup when I try using custom Lora I downloaded in Custom Download Corner, the error as follow :

16:03:42-375105 ERROR gradio call: RuntimeError
╭───────────────────── Traceback (most recent call last) ──────────────────────╮
│ /content/vladmandic-webui/modules/call_queue.py:59 in f │
│ │
│ 58 │ │ │ │ pr.enable() │
│ ❱ 59 │ │ │ res = list(func(*args, **kwargs)) │
│ 60 │ │ │ if shared.cmd_opts.profile: │
│ │
│ /content/vladmandic-webui/modules/call_queue.py:38 in f │
│ │
│ 37 │ │ │ try: │
│ ❱ 38 │ │ │ │ res = func(*args, **kwargs) │
│ 39 │ │ │ │ progress.record_results(id_task, res) │
│ │
│ ... 26 frames hidden ... │
│ │
│ /content/vladmandic-webui/extensions-builtin/a1111-sd-webui-lycoris/lycoris. │
│ py:734 in lyco_Linear_forward │
│ │
│ 733 │ │
│ ❱ 734 │ return torch.nn.Linear_forward_before_lyco(self, input) │
│ 735 │
│ │
│ /usr/local/lib/python3.10/dist-packages/torch/nn/modules/linear.py:114 in │
│ forward │
│ │
│ 113 │ def forward(self, input: Tensor) -> Tensor: │
│ ❱ 114 │ │ return F.linear(input, self.weight, self.bias) │
│ 115 │
╰──────────────────────────────────────────────────────────────────────────────╯
RuntimeError: Expected all tensors to be on the same device, but found at least
two devices, cuda:0 and cpu! (when checking argument for argument mat2 in method
wrapper_CUDA_mm)

this is the first time for me trying to use Lora, so I dont understand what's happening. But using the already installed embeddings are no issue

How can I install the web-UI on my GDrive besides the local session storage? I wish to use the models I have stored on my GDrive.