kijai / ComfyUI-KwaiKolorsWrapper

Diffusers wrapper to run Kwai-Kolors model
Apache License 2.0
561 stars 29 forks source link

RuntimeError: Only Tensors of floating point and complex dtype can require gradients #33

Open nyukers opened 4 months ago

nyukers commented 4 months ago

Windows 10 22H2, GeForce GTX 1080Ti, VRAM 11Gb, CUDA v12.6

Load TEXT_ENCODER... !!! Exception during processing!!! Only Tensors of floating point and complex dtype can require gradients Traceback (most recent call last): File "d:\SDComfyUI\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "d:\SDComfyUI\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:\SDComfyUI\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(slice_dict(input_data_all, i))) File "D:\SDComfyUI\ComfyUI\custom_nodes\ComfyUI-KwaiKolorsWrapper\nodes.py", line 124, in loadmodel text_encoder.quantize(8) File "D:\SDComfyUI\ComfyUI\custom_nodes\ComfyUI-KwaiKolorsWrapper\kolors\models\modeling_chatglm.py", line 852, in quantize quantize(self.encoder, weight_bit_width) File "D:\SDComfyUI\ComfyUI\custom_nodes\ComfyUI-KwaiKolorsWrapper\kolors\models\quantization.py", line 155, in quantize layer.self_attention.query_key_value = QuantizedLinear( File "D:\SDComfyUI\ComfyUI\custom_nodes\ComfyUI-KwaiKolorsWrapper\kolors\models\quantization.py", line 141, in init self.weight = Parameter(self.weight.to(device), requires_grad=False) File "d:\SDComfyUI\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1632, in setattr self.register_parameter(name, value) File "d:\SDComfyUI\python_embeded\lib\site-packages\accelerate\big_modeling.py", line 105, in register_empty_parameter module._parameters[name] = param_cls(module._parameters[name].to(device), kwargs) File "d:\SDComfyUI\python_embeded\lib\site-packages\torch\nn\parameter.py", line 36, in new return torch.Tensor._make_subclass(cls, data, requires_grad) RuntimeError: Only Tensors of floating point and complex dtype can require gradients