# RuntimeError: expected scalar type BFloat16 but found Half

**URL:** <https://discuss.huggingface.co/t/runtimeerror-expected-scalar-type-bfloat16-but-found-half/23864>\
**Category:** Beginners\
**Created:** [October 1, 2022, 2:12pm UTC](https://discuss.huggingface.co/t/runtimeerror-expected-scalar-type-bfloat16-but-found-half/23864 "2022-10-01T14:12:57Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![nightfury](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/nightfury/32/39775_2.png) [@nightfury](https://discuss.huggingface.co/u/nightfury)\
**Post date:** [October 1, 2022, 2:12pm UTC](https://discuss.huggingface.co/t/runtimeerror-expected-scalar-type-bfloat16-but-found-half/23864/1 "2022-10-01T14:12:57Z")

</div>

```auto
Traceback (most recent call last):
  File "app_sd.py", line 35, in <module>
    images = pipe(prompt=prompt, init_image=init_image, strength=0.75, guidance_scale=7.5).images
  File "/home/user/.local/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "/home/user/.local/lib/python3.8/site-packages/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py", line 198, in __call__
    init_latent_dist = self.vae.encode(init_image.to(self.device)).latent_dist
  File "/home/user/.local/lib/python3.8/site-packages/diffusers/models/vae.py", line 549, in encode
    h = self.encoder(x)
  File "/home/user/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/user/.local/lib/python3.8/site-packages/diffusers/models/vae.py", line 121, in forward
    sample = down_block(sample)
  File "/home/user/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/user/.local/lib/python3.8/site-packages/diffusers/models/unet_blocks.py", line 708, in forward
    hidden_states = resnet(hidden_states, temb=None)
  File "/home/user/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/user/.local/lib/python3.8/site-packages/diffusers/models/resnet.py", line 334, in forward
    hidden_states = self.norm1(hidden_states).type(hidden_states.dtype)
  File "/home/user/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/user/.local/lib/python3.8/site-packages/torch/nn/modules/normalization.py", line 272, in forward
    return F.group_norm(
  File "/home/user/.local/lib/python3.8/site-packages/torch/nn/functional.py", line 2516, in group_norm
    return torch.group_norm(input, num_groups, weight, bias, eps, torch.backends.cudnn.enabled)
RuntimeError: expected scalar type BFloat16 but found Half

```

> **[app\_sd.py · nightfury/Stable\_Diffusion at main](https://huggingface.co/spaces/nightfury/Stable_Diffusion/blob/main/app_sd.py)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.