Text2Art is an AI art generator powered with VQGAN + CLIP and CLIPDrawer models

Hi, thank you for sharing this repo. I wondered if you could help me get it to run in the Colab, because it does not seem run as-is. I know Python but I am a noob in this ML domain.

Off the bat it was failing on import clipit on a call to torchtext which appeared to be versioning issue. I added !pip install -U torchtextwhich then led to this failure further down the code.

RuntimeError                              Traceback (most recent call last)
<ipython-input-2-25d790141602> in <module>()
     12 # Apply these settings and run
     13 settings = clipit.apply_settings()
---> 14 clipit.do_init(settings)
     15 clipit.do_run(settings)

1 frames

/usr/local/lib/python3.7/dist-packages/torch/jit/_script.py in fail(self, *args, **kwargs)
    912     def _make_fail(name):
    913         def fail(self, *args, **kwargs):
--> 914             raise RuntimeError(name + " is not supported on ScriptModules")
    915 
    916         return fail

RuntimeError: requires_grad_ is not supported on ScriptModules

Hi there,

When I try to run your Google Colab notebook, I got an error that says:

AttributeError Traceback (most recent call last) in () 13 settings = clipit.apply_settings() 14 clipit.do_init(settings) ---> 15 clipit.do_run(settings)

11 frames /usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py in getattr(self, name) 1129 return modules[name] 1130 raise AttributeError("'{}' object has no attribute '{}'".format( -> 1131 type(self).name, name)) 1132 1133 def setattr(self, name: str, value: Union[Tensor, 'Module']) -> None:

AttributeError: 'MyRandomPerspective' object has no attribute 'resample'

Could you please help? Thanks!

ImportError Traceback (most recent call last) in () ----> 1 import clipit 2 # To reset settings to default 3 clipit.reset_settings() 4 # You can use "|" to separate multiple prompts 5 prompts = "underwater city"

10 frames /usr/local/lib/python3.7/dist-packages/torch_xla/init.py in () 126 import torch 127 from ._patched_functions import _apply_patches --> 128 import _XLAC 129 130

ImportError: /usr/local/lib/python3.7/dist-packages/_XLAC.cpython-37m-x86_64-linux-gnu.so: undefined symbol: _ZN2at11result_typeERKNS_6TensorEN3c106ScalarE

NOTE: If your import is failing due to a missing package, you can manually install dependencies using either !pip or !apt.

To view examples of installing some common dependencies, click the "Open Examples" button below.

AttributeError Traceback (most recent call last) in () 1 import clipit 2 # To reset settings to default ----> 3 clipit.reset_settings() 4 # You can use "|" to separate multiple prompts 5 prompts = "death sky rain"

AttributeError: module 'clipit' has no attribute 'reset_settings'

Always get this error when using the Colab. I run setup, restart runtime and then execute the next block. It breaks then.

First I was getting error like :

RuntimeError: requires_grad_ is not supported on ScriptModules

Found one solution at : https://githubhelp.com/mfrashad/text2art/issues/5 Solution says change version of tochtext to torchtext==0.10.0 So installed using : pip install torchtext==0.10.0 It changed torch version to 1.9.0 from 1.10.0

Now getting another error :

/home/ubuntu/anaconda3/envs/textToArt/lib/python3.7/site-packages/torchvision/io/image.py:11: UserWarning: Failed to load image Python extension: /home/ubuntu/anaconda3/envs/textToArt/lib/python3.7/site-packages/torchvision/image.so: undefined symbol: _ZNK2at10TensorBase21__dispatch_contiguousEN3c1012MemoryFormatE warn(f"Failed to load image Python extension: {e}") Segmentation fault (core dumped)

Hi, trying to run this from Google Colab, returns this error:

ImportError                               Traceback (most recent call last)
<ipython-input-17-25d790141602> in <module>()
----> 1 import clipit
      2 # To reset settings to default
      3 clipit.reset_settings()
      4 # You can use "|" to separate multiple prompts
      5 prompts = "underwater city"

/content/clipit/clipit.py in <module>()
     22 #torch.use_deterministic_algorithms(True)               # NR: grid_sampler_2d_backward_cuda does not have a deterministic implementation
     23 
---> 24 from torch_optimizer import DiffGrad, AdamP, RAdam
     25 from perlin_numpy import generate_fractal_noise_2d
     26 

ImportError: cannot import name 'RAdam' from 'torch_optimizer' (/usr/local/lib/python3.7/dist-packages/torch_optimizer/__init__.py)

please help here is the error 👇:

`AttributeError
Traceback (most recent call last) /tmp/ipykernel_32/3491049020.py in 1 import clipit 2 # To reset settings to default ----> 3 clipit.reset_settings() 4 # You can use "|" to separate multiple prompts 5 prompts = "underwater city"

AttributeError: module 'clipit' has no attribute 'reset_settings'

`

ModuleNotFoundError Traceback (most recent call last) in 1 import sys 2 sys.path.append("clipit") ----> 3 import clipit 4 5 # To reset settings to default

/content/clipit/clipit.py in 25 from perlin_numpy import generate_fractal_noise_2d 26 ---> 27 from CLIP import clip 28 import kornia 29 import kornia.augmentation as K

ModuleNotFoundError: No module named 'CLIP'

NOTE: If your import is failing due to a missing package, you can manually install dependencies using either !pip or !apt.

To view examples of installing some common dependencies, click the "Open Examples" button below.

```Working` with z of shape (1, 256, 16, 16) = 65536 dimensions. loaded pretrained LPIPS loss from taming/modules/autoencoder/lpips/vgg.pth VQLPIPSWithDiscriminator running with hinge loss. Restored from models/vqgan_imagenet_f16_16384.ckpt Using device: cuda:0 Optimising using: Adam Using text prompts: ['underwater city'] Using seed: 1698681138380486500 0/? [00:00<?, ?it/s] Oops: runtime error: solve: MAGMA library not found in compilation. Please rebuild with MAGMA. Try reducing --num-cuts to save memory

RuntimeError Traceback (most recent call last) /tmp/ipykernel_58/2225298613.py in 21 settings = clipit.apply_settings() 22 clipit.do_init(settings) ---> 23 clipit.do_run(settings)

/kaggle/working/clipit/clipit.py in do_run(args) 997 print("Oops: runtime error: ", e) 998 print("Try reducing --num-cuts to save memory") --> 999 raise e 1000 except KeyboardInterrupt: 1001 pass

/kaggle/working/clipit/clipit.py in do_run(args) 989 while True: 990 try: --> 991 train(args, cur_iteration) 992 if cur_iteration == args.iterations: 993 break

/kaggle/working/clipit/clipit.py in train(args, cur_it) 902 903 for i in range(args.batches): --> 904 lossAll = ascend_txt(args) 905 906 if i == 0 and cur_it % args.save_every == 0:

/kaggle/working/clipit/clipit.py in ascend_txt(args) 723 for cutoutSize in cutoutsTable: 724 make_cutouts = cutoutsTable[cutoutSize] --> 725 cur_cutouts[cutoutSize] = make_cutouts(out) 726 727 if args.spot_prompts:

/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs) 1049 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks 1050 or _global_forward_hooks or _global_forward_pre_hooks): -> 1051 return forward_call(*input, **kwargs) 1052 # Do not call functions when jit is used 1053 full_backward_hooks, non_full_backward_hooks = [], []

/kaggle/working/clipit/clipit.py in forward(self, input, spot) 352 # TF.to_pil_image(batch[j_wide].cpu()).save(f"cached_im_{cur_iteration:02d}{j_wide:02d}{spot}.png") 353 else: --> 354 batch1, transforms1 = self.augs_zoom(torch.cat(cutouts[:self.cutn_zoom], dim=0)) 355 batch2, transforms2 = self.augs_wide(torch.cat(cutouts[self.cutn_zoom:], dim=0)) 356 # print(batch1.shape, batch2.shape)

/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs) 1049 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks 1050 or _global_forward_hooks or _global_forward_pre_hooks): -> 1051 return forward_call(*input, **kwargs) 1052 # Do not call functions when jit is used 1053 full_backward_hooks, non_full_backward_hooks = [], []

/opt/conda/lib/python3.7/site-packages/torch/nn/modules/container.py in forward(self, input) 137 def forward(self, input): 138 for module in self: --> 139 input = module(input) 140 return input 141

/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs) 1049 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks 1050 or _global_forward_hooks or _global_forward_pre_hooks): -> 1051 return forward_call(*input, **kwargs) 1052 # Do not call functions when jit is used 1053 full_backward_hooks, non_full_backward_hooks = [], []

/opt/conda/lib/python3.7/site-packages/kornia/augmentation/augmentation.py in forward(self, input, params, return_transform) 1141 input_pad = self.compute_padding(input_temp.shape) 1142 _input = self.precrop_padding(input_temp, input_pad) # type: ignore -> 1143 out = super().forward(_input, params, return_transform) 1144 1145 # Update the actual input size for inverse

/opt/conda/lib/python3.7/site-packages/kornia/augmentation/base.py in forward(self, input, params, return_transform) 243 244 self._params = params --> 245 output = self.apply_func(in_tensor, in_transform, self._params, return_transform) 246 return _transform_output_shape(output, ori_shape) if self.keepdim else output 247

/opt/conda/lib/python3.7/site-packages/kornia/augmentation/base.py in apply_func(self, in_tensor, in_transform, params, return_transform) 202 # if all data needs to be augmented 203 elif torch.sum(to_apply) == len(to_apply): --> 204 trans_matrix = self.compute_transformation(in_tensor, params) 205 output = self.apply_transform(in_tensor, params, trans_matrix) 206 else:

/opt/conda/lib/python3.7/site-packages/kornia/augmentation/augmentation.py in compute_transformation(self, input, params) 1063 1064 def compute_transformation(self, input: torch.Tensor, params: Dict[str, torch.Tensor]) -> torch.Tensor: -> 1065 transform: torch.Tensor = get_perspective_transform(params['src'].to(input), params['dst'].to(input)) 1066 return transform 1067

/opt/conda/lib/python3.7/site-packages/kornia/geometry/transform/imgwarp.py in get_perspective_transform(src, dst) 281 282 # solve the system Ax = b --> 283 X, LU = _torch_solve_cast(b, A) 284 285 # create variable to return

/opt/conda/lib/python3.7/site-packages/kornia/utils/helpers.py in _torch_solve_cast(input, A) 94 dtype = torch.float32 95 ---> 96 out1, out2 = torch.solve(input.to(dtype), A.to(dtype)) 97 98 return (out1.to(input.dtype), out2.to(input.dtype))

RuntimeError: solve: MAGMA library not found in compilation. Please rebuild with MAGMA.```

here is the kaggle code please fix it 😭 https://www.kaggle.com/shreeshaaithal/notebookf22d408364

Hi there

I keep getting this issue when I try and run VQGAN + CLIP

RuntimeError Traceback (most recent call last) in () 12 # Apply these settings and run 13 settings = clipit.apply_settings() ---> 14 clipit.do_init(settings) 15 clipit.do_run(settings)

4 frames /usr/local/lib/python3.7/dist-packages/torch/serialization.py in init(self, name_or_buffer) 240 class _open_zipfile_reader(_opener): 241 def init(self, name_or_buffer) -> None: --> 242 super(_open_zipfile_reader, self).init(torch._C.PyTorchFileReader(name_or_buffer)) 243 244

RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory