RuntimeError: CUDA error: invalid argument

[fikry102]

python demo.py

Random Seed 9999, Style Control [Start Step, End Step] = [5, 30], Style Control Layer Index = [20, 22, 24, 26, 28, 30]
Global seed set to 9999
text_config_dict is provided which will be used to initialize CLIPTextConfig. The value text_config["id2label"] will be overriden.
DDIM inversion...
Null-text optimization...
0%| | 0/30 [00:00<?, ?it/s]
Traceback (most recent call last):
File "demo.py", line 442, in
main()
File "demo.py", line 370, in main
_, content_latent_list, x_t, uncond_embeddings = null_inversion.invert(
File "demo.py", line 306, in invert
uncond_embeddings = self.null_optimization(
File "demo.py", line 279, in null_optimization
loss.backward()
File "/home/cvmt/anaconda3/envs/zstar/lib/python3.8/site-packages/torch/_tensor.py", line 487, in backward
torch.autograd.backward(
File "/home/cvmt/anaconda3/envs/zstar/lib/python3.8/site-packages/torch/autograd/init.py", line 200, in backward
Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
RuntimeError: CUDA error: invalid argument
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.