File name too long

[raisedconfused]

first time user, tried with default settings after not being able to with custom ones. getting this error message

apologies if this is a dumb question

Cleared Accounted PIDs for GPU 00000000:00:04.0. All done. Using device: cuda:0 Using seed: 17729675578306137288

OSError Traceback (most recent call last)

in () 34 print('Using seed:', seed) 35 ---> 36 model = load_vqgan_model(args.vqgan_config, args.vqgan_checkpoint).to(device) 37 perceptor = clip.load(args.clip_model, jit=False)[0].eval().requires_grad_(False).to(device) 38 1 frames /usr/local/lib/python3.7/dist-packages/omegaconf/omegaconf.py in load(file_) 181 182 if isinstance(file_, (str, pathlib.Path)): --> 183 with io.open(os.path.abspath(file_), "r", encoding="utf-8") as f: 184 obj = yaml.load(f, Loader=get_yaml_loader()) 185 elif getattr(file_, "read", None): OSError: [Errno 36] File name too long: '/content/VQModel(\n (encoder): Encoder(\n (conv_in): Conv2d(3, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n (down): ModuleList(\n (0): Module(\n (block): ModuleList(\n (0): ResnetBlock(\n (norm1): GroupNorm(32, 128, eps=1e-06, affine=True)\n (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n (norm2): GroupNorm(32, 128, eps=1e-06, affine=True)\n (dropout): Dropout(p=0.0, inplace=False)\n (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n )\n (1): ResnetBlock(\n (norm1): GroupNorm(32, 128, eps=1e-06, affine=True)\n (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n (norm2): GroupNorm(32, 128, eps=1e-06, affine=True)\n (dropout): Dropout(p=0.0, inplace=False)\n (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n )\n )\n (attn): ModuleList()\n (downsample): Downsample(\n (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2))\n )\n )\n (1): Module(\n (block): ModuleList(\n (0): ResnetBlock(\n (norm1): GroupNorm(32, 128, eps=1e-06, affine=True)\n (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))\n (norm2): GroupNorm(32...

[chigozienri]

Hmm, I think this used to happen if you cut off the generation half way through and didn't re-run the parameters cell, but I thought I fixed that. Are you using the most up-to-date version?

Can you do three things for me?

1. Can you click on where the error message has that up down arrow and "1 frames", and take another screenshot of what happened in between?

2. Can you make a new cell, and run print(args.vqgan_config)?

3. Can you copy and paste the URL of the page you're accessing so I can be sure you're not somehow using an old version?

I'm very confused how you got into this state.

Sorry it took me a while to respond! Hope we can get it fixed for you.