Update schedulers.md

stevhliu · web-flow · commit e52d28d4884f · 2025-07-02T15:41:11.000-07:00
diff --git a/docs/source/en/using-diffusers/schedulers.md b/docs/source/en/using-diffusers/schedulers.md
@@ -251,6 +251,6 @@ from diffusers import AutoModel
 unet = AutoModel.from_pretrained(
     "stabilityai/stable-diffusion-xl-base-1.0", subfolder="unet", torch_dtype=torch.float16
 )
-
+```
 
 You can also use the [torch.Tensor.to](https://docs.pytorch.org/docs/stable/generated/torch.Tensor.to.html) method to convert to the specified dtype on the fly. It converts *all* weights unlike the `torch_dtype` argument that respects the `_keep_in_fp32_modules`. This is important for models whose layers must remain in fp32 for numerical stability and best generation quality (see example [here](https://github.com/huggingface/diffusers/blob/f864a9a352fa4a220d860bfdd1782e3e5af96382/src/diffusers/models/transformers/transformer_wan.py#L374)).

Original file line number	Diff line number	Diff line change
`@@ -251,6 +251,6 @@ from diffusers import AutoModel`
`251`	`251`	`unet = AutoModel.from_pretrained(`
`252`	`252`	`"stabilityai/stable-diffusion-xl-base-1.0", subfolder="unet", torch_dtype=torch.float16`
`253`	`253`	`)`
`254`		`-`
	`254`	+```
`255`	`255`
`256`	`256`	You can also use the [torch.Tensor.to](https://docs.pytorch.org/docs/stable/generated/torch.Tensor.to.html) method to convert to the specified dtype on the fly. It converts all weights unlike the `torch_dtype` argument that respects the `_keep_in_fp32_modules`. This is important for models whose layers must remain in fp32 for numerical stability and best generation quality (see example [here](https://github.com/huggingface/diffusers/blob/f864a9a352fa4a220d860bfdd1782e3e5af96382/src/diffusers/models/transformers/transformer_wan.py#L374)).