-
Notifications
You must be signed in to change notification settings - Fork 14
Description
When I modify the prompt in run.sh, I sometimes encounter the following error, which causes the SR step and subsequent reconstruction to fail.
However, what's strange is that the original prompt in the script and other prompts can run without any issues.
Traceback (most recent call last):
File "/mnt/lpai-dione/ssai/cvg/team/fenghe/code/LayerPano3D/gen_layerdata.py", line 226, in
pano_pred_pil = pipe(
File "/mnt/lpai-dione/ssai/cvg/team/fenghe/conda_envs/layerpano3d/lib/python3.9/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
File "/mnt/lpai-dione/ssai/cvg/team/fenghe/code/LayerPano3D/src/pipeline_flux_fill.py", line 961, in call
noise_pred = self.transformer(
File "/mnt/lpai-dione/ssai/cvg/team/fenghe/conda_envs/layerpano3d/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/mnt/lpai-dione/ssai/cvg/team/fenghe/conda_envs/layerpano3d/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "/mnt/lpai-dione/ssai/cvg/team/fenghe/conda_envs/layerpano3d/lib/python3.9/site-packages/accelerate/hooks.py", line 175, in new_forward
output = module._old_forward(*args, **kwargs)
File "/mnt/lpai-dione/ssai/cvg/team/fenghe/conda_envs/layerpano3d/lib/python3.9/site-packages/diffusers/models/transformers/transformer_flux.py", line 463, in forward
hidden_states = self.x_embedder(hidden_states)
File "/mnt/lpai-dione/ssai/cvg/team/fenghe/conda_envs/layerpano3d/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/mnt/lpai-dione/ssai/cvg/team/fenghe/conda_envs/layerpano3d/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "/mnt/lpai-dione/ssai/cvg/team/fenghe/conda_envs/layerpano3d/lib/python3.9/site-packages/torch/nn/modules/linear.py", line 117, in forward
return F.linear(input, self.weight, self.bias)
RuntimeError: mat1 and mat2 shapes cannot be multiplied (8192x384 and 64x3072)