i use linux ,follow the steps,and not using Use half floats to generate Unet.plan file,but when I drew the picture, the above error appeared : AttributeError: 'NoneType' object has no attribute 'set_binding_shape' in
File "/root/stable-diffusion-webui/modules/sd_unet.py", line 89, in UNetModel_forward
return current_unet.forward(x, timesteps, context, *args, **kwargs)
File "/root/stable-diffusion-webui/extensions/stable-diffusion-webui-tensorr-sdxl/scripts/trt_sdxl.py", line 91, in forward
noise_pred = self.infer({"x": x, "timesteps": timesteps, "context": context[:,:154,:], "y":y[:,:1280]})
File "/root/stable-diffusion-webui/extensions/stable-diffusion-webui-tensorr-sdxl/scripts/trt_sdxl.py", line 86, in infer
self.allocate_buffers(batch_size, image_width, image_height)
File "/root/stable-diffusion-webui/extensions/stable-diffusion-webui-tensorr-sdxl/scripts/trt_sdxl.py", line 65, in allocate_buffers
self.engine.allocate_buffers(shape_dict=get_shape_dict(batch_size, image_height, image_width),
File "/root/stable-diffusion-webui/extensions/stable-diffusion-webui-tensorr-sdxl/utilities.py", line 270, in allocate_buffers
self.context.set_binding_shape(idx, shape)
i use linux ,follow the steps,and not using Use half floats to generate Unet.plan file,but when I drew the picture, the above error appeared : AttributeError: 'NoneType' object has no attribute 'set_binding_shape' in File "/root/stable-diffusion-webui/modules/sd_unet.py", line 89, in UNetModel_forward return current_unet.forward(x, timesteps, context, *args, **kwargs) File "/root/stable-diffusion-webui/extensions/stable-diffusion-webui-tensorr-sdxl/scripts/trt_sdxl.py", line 91, in forward noise_pred = self.infer({"x": x, "timesteps": timesteps, "context": context[:,:154,:], "y":y[:,:1280]}) File "/root/stable-diffusion-webui/extensions/stable-diffusion-webui-tensorr-sdxl/scripts/trt_sdxl.py", line 86, in infer self.allocate_buffers(batch_size, image_width, image_height) File "/root/stable-diffusion-webui/extensions/stable-diffusion-webui-tensorr-sdxl/scripts/trt_sdxl.py", line 65, in allocate_buffers self.engine.allocate_buffers(shape_dict=get_shape_dict(batch_size, image_height, image_width), File "/root/stable-diffusion-webui/extensions/stable-diffusion-webui-tensorr-sdxl/utilities.py", line 270, in allocate_buffers self.context.set_binding_shape(idx, shape)