TencentQQGYLab / ComfyUI-ELLA

ELLA nodes for ComfyUI
298 stars 13 forks source link

Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! #46

Open teanhow opened 1 month ago

teanhow commented 1 month ago

在ella text Encode提示出错

Error occurred when executing EllaTextEncode:

Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!

File "D:\comfyui\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\comfyui\execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\comfyui\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\comfyui\custom_nodes\ComfyUI-ELLA\ella.py", line 289, in encode ella_conds = ella_encode(ella["model"], timesteps, embeds) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\comfyui\custom_nodes\ComfyUI-ELLA\ella.py", line 42, in ella_encode cond_ella = ella(timestep, embeds) ^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\comfyui\custom_nodes\ComfyUI-ELLA\model.py", line 330, in call cond = self.model(timesteps, t5_embeds, kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\comfyui.ext\Lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl return self._call_impl(*args, *kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\comfyui.ext\Lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl return forward_call(args, kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\comfyui\custom_nodes\ComfyUI-ELLA\model.py", line 308, in forward return self.connector(t5_embeds, timestep_embedding=time_embedding) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\comfyui.ext\Lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl return self._call_impl(*args, *kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\comfyui.ext\Lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl return forward_call(args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\comfyui\custom_nodes\ComfyUI-ELLA\model.py", line 106, in forward latents = learnable_latents + self.time_aware_linear(torch.nn.functional.silu(timestep_embedding))

我的显存不大3080 10G,windows 11环境,是采用了共享显存的模式在运行comfyUI。

JettHu commented 1 month ago

comfyui 的启动命令是什么