There is an error, how can I fixed this?
KenwoodID opened this issue · 3 comments
Thanks
Did you by any chance change the model? if so what model did you try to use?
I did not change the model, using the default one. models--Lykon--dreamshaper-7
met the same Error, and the detail tracking info is as below
inference starts 0%| | 0/3 [00:00<?, ?it/s] inference took 2.0s Traceback (most recent call last): File "/Users/gagao7/SourceCode/github/flowty-realtime-lcm-canvas/env/lib/python3.9/site-packages/gradio/routes.py", line 488, in run_predict output = await app.get_blocks().process_api( File "/Users/gagao7/SourceCode/github/flowty-realtime-lcm-canvas/env/lib/python3.9/site-packages/gradio/blocks.py", line 1431, in process_api result = await self.call_function( File "/Users/gagao7/SourceCode/github/flowty-realtime-lcm-canvas/env/lib/python3.9/site-packages/gradio/blocks.py", line 1103, in call_function prediction = await anyio.to_thread.run_sync( File "/Users/gagao7/SourceCode/github/flowty-realtime-lcm-canvas/env/lib/python3.9/site-packages/anyio/to_thread.py", line 33, in run_sync return await get_asynclib().run_sync_in_worker_thread( File "/Users/gagao7/SourceCode/github/flowty-realtime-lcm-canvas/env/lib/python3.9/site-packages/anyio/_backends/_asyncio.py", line 877, in run_sync_in_worker_thread return await future File "/Users/gagao7/SourceCode/github/flowty-realtime-lcm-canvas/env/lib/python3.9/site-packages/anyio/_backends/_asyncio.py", line 807, in run result = context.run(func, *args) File "/Users/gagao7/SourceCode/github/flowty-realtime-lcm-canvas/env/lib/python3.9/site-packages/gradio/utils.py", line 707, in wrapper response = f(*args, **kwargs) File "/Users/gagao7/SourceCode/github/flowty-realtime-lcm-canvas/ui.py", line 33, in process_image return infer( File "/Users/gagao7/SourceCode/github/flowty-realtime-lcm-canvas/main.py", line 94, in infer return pipe( File "/Users/gagao7/SourceCode/github/flowty-realtime-lcm-canvas/env/lib/python3.9/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) File "/Users/gagao7/SourceCode/github/flowty-realtime-lcm-canvas/env/lib/python3.9/site-packages/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py", line 891, in __call__ noise_pred = self.unet( File "/Users/gagao7/SourceCode/github/flowty-realtime-lcm-canvas/env/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "/Users/gagao7/SourceCode/github/flowty-realtime-lcm-canvas/env/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) File "/Users/gagao7/SourceCode/github/flowty-realtime-lcm-canvas/env/lib/python3.9/site-packages/diffusers/models/unet_2d_condition.py", line 1142, in forward sample = upsample_block( File "/Users/gagao7/SourceCode/github/flowty-realtime-lcm-canvas/env/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "/Users/gagao7/SourceCode/github/flowty-realtime-lcm-canvas/env/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) File "/Users/gagao7/SourceCode/github/flowty-realtime-lcm-canvas/env/lib/python3.9/site-packages/diffusers/models/unet_2d_blocks.py", line 2475, in forward hidden_states = upsampler(hidden_states, upsample_size, scale=scale) File "/Users/gagao7/SourceCode/github/flowty-realtime-lcm-canvas/env/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "/Users/gagao7/SourceCode/github/flowty-realtime-lcm-canvas/env/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) File "/Users/gagao7/SourceCode/github/flowty-realtime-lcm-canvas/env/lib/python3.9/site-packages/diffusers/models/resnet.py", line 187, in forward hidden_states = F.interpolate(hidden_states, scale_factor=2.0, mode="nearest") File "/Users/gagao7/SourceCode/github/flowty-realtime-lcm-canvas/env/lib/python3.9/site-packages/torch/nn/functional.py", line 3983, in interpolate return torch._C._nn.upsample_nearest2d(input, output_size, scale_factors) RuntimeError: "upsample_nearest2d_channels_last" not implemented for 'Half'