Input type (float) and bias type (c10::Half) should be the same

[onoregleb]

Can you tell me how this can be fixed? Has anyone encountered this?

/home/jupyter/.local/lib/python3.10/site-packages/transformers/utils/hub.py:123: FutureWarning: Using TRANSFORMERS_CACHE is deprecated and will be removed in v5 of Transformers. Use HF_HOME instead.
warnings.warn(
2024-11-14 10:05:34.975789: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
Loading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 166.46it/s]
text_config_dict is provided which will be used to initialize CLIPTextConfig. The value text_config["id2label"] will be overriden.
text_config_dict is provided which will be used to initialize CLIPTextConfig. The value text_config["bos_token_id"] will be overriden.
text_config_dict is provided which will be used to initialize CLIPTextConfig. The value text_config["eos_token_id"] will be overriden.
100%|██████████| 1/1 [00:00<00:00, 1.09it/s]
100%|██████████| 1/1 [00:01<00:00, 1.39s/it]
Traceback (most recent call last):
File "/home/jupyter/datasphere/project/OOTDiffusion/run/run_ootd.py", line 71, in
images = model(
File "/home/jupyter/datasphere/project/OOTDiffusion/ootd/inference_ootd_dc.py", line 126, in call
images = self.pipe(prompt_embeds=prompt_embeds,
File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/home/jupyter/datasphere/project/OOTDiffusion/ootd/pipelines_ootd/pipeline_ootd.py", line 306, in call
garm_latents = self.prepare_garm_latents(
File "/home/jupyter/datasphere/project/OOTDiffusion/ootd/pipelines_ootd/pipeline_ootd.py", line 726, in prepare_garm_latents
image_latents = self.vae.encode(image).latent_dist.mode()
File "/home/jupyter/.local/lib/python3.10/site-packages/diffusers/utils/accelerate_utils.py", line 46, in wrapper
return method(self, *args, **kwargs)
File "/home/jupyter/.local/lib/python3.10/site-packages/diffusers/models/autoencoder_kl.py", line 259, in encode
h = self.encoder(x)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/jupyter/.local/lib/python3.10/site-packages/diffusers/models/vae.py", line 141, in forward
sample = self.conv_in(sample)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/conv.py", line 463, in forward
return self._conv_forward(input, self.weight, self.bias)
File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/conv.py", line 459, in _conv_forward
return F.conv2d(input, weight, bias, self.stride,
RuntimeError: Input type (float) and bias type (c10::Half) should be the same