Open djay29 opened 1 year ago
This is with vid2vid on AMD graphics card using DML
@djay29 did you manage to get txt2vid or vid2vid to work on an AMD card? How did you do that?
@system3600 It is not working on AMD gpus. It was able generate only one frame in txt2vid after that there is another error which is also reported by me in issue #123
An exception occurred while trying to process the frame: tensor.device().type() == at::DeviceType::PrivateUse1 INTERNAL ASSERT FAILED at "D:\a\_work\1\s\pytorch-directml-plugin\torch_directml\csrc\dml\DMLTensor.cpp":31, please report a bug to PyTorch. unbox expects Dml at::Tensor as inputs Traceback (most recent call last): File "E:\stable-diffusion-webui-directml\extensions\SD-CN-Animation\scripts\base_ui.py", line 139, in process yield from vid2vid.start_process(args) File "E:\stable-diffusion-webui-directml\extensions\SD-CN-Animation\scripts\core\vid2vid.py", line 149, in start_process next_flow, prev_flow, occlusion_mask = RAFT_estimate_flow(prev_frame, curr_frame, device=device) File "E:\stable-diffusion-webui-directml\extensions\SD-CN-Animation\scripts\core\flow_utils.py", line 69, in RAFT_estimateflow , next_flow = RAFT_model(image1, image2, iters=20, test_mode=True) File "E:\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(args, kwargs) File "E:\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\parallel\data_parallel.py", line 153, in forward return self.module(*inputs, *kwargs) File "E:\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(args, kwargs) File "E:\stable-diffusion-webui-directml\extensions\SD-CN-Animation\RAFT\raft.py", line 100, in forward fmap1, fmap2 = self.fnet([image1, image2]) File "E:\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, kwargs) File "E:\stable-diffusion-webui-directml\extensions\SD-CN-Animation\RAFT\extractor.py", line 176, in forward x = self.conv1(x) File "E:\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, *kwargs) File "E:\stable-diffusion-webui-directml\extensions-builtin\Lora\lora.py", line 376, in lora_Conv2d_forward return torch.nn.Conv2d_forward_before_lora(self, input) File "E:\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\conv.py", line 463, in forward return self._conv_forward(input, self.weight, self.bias) File "E:\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\conv.py", line 459, in _conv_forward return F.conv2d(input, weight, bias, self.stride, File "E:\stable-diffusion-webui-directml\modules\dml\amp\autocast_mode.py", line 32, in
setattr(resolved_obj, func_path[-1], lambda args, kwargs: pre_forward(op, args, kwargs))
File "E:\stable-diffusion-webui-directml\modules\dml\amp\autocast_mode.py", line 9, in pre_forward
return forward(*args, **kwargs)
RuntimeError: tensor.device().type() == at::DeviceType::PrivateUse1 INTERNAL ASSERT FAILED at "D:\a\_work\1\s\pytorch-directml-plugin\torch_directml\csrc\dml\DMLTensor.cpp":31, please report a bug to PyTorch. unbox expects Dml at::Tensor as inputs