Fix typos

docs/source/en/api/pipelines/pixart.md

@@ -37,7 +37,7 @@ Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.m
 
 ## Inference with under 8GB GPU VRAM
 
-Run the [`PixArtAlphaPipeline`] with under 8GB GPU VRAM by loading the text encoder in 8-bit precision. Let's walk through a full-fledged example. 
+Run the [`PixArtAlphaPipeline`] with under 8GB GPU VRAM by loading the text encoder in 8-bit precision. Let's walk through a full-fledged example.
 
 First, install the [bitsandbytes](https://github.com/TimDettmers/bitsandbytes) library:
 
@@ -75,10 +75,10 @@ with torch.no_grad():
     prompt_embeds, prompt_attention_mask, negative_embeds, negative_prompt_attention_mask = pipe.encode_prompt(prompt)
 ```
 
-Since text embeddings have been computed, remove the `text_encoder` and `pipe` from the memory, and free up som GPU VRAM:
+Since text embeddings have been computed, remove the `text_encoder` and `pipe` from the memory, and free up some GPU VRAM:
 
 ```python
-import gc 
+import gc
 
 def flush():
     gc.collect()
@@ -99,7 +99,7 @@ pipe = PixArtAlphaPipeline.from_pretrained(
 ).to("cuda")
 
 latents = pipe(
-    negative_prompt=None, 
+    negative_prompt=None,
     prompt_embeds=prompt_embeds,
     negative_prompt_embeds=negative_embeds,
     prompt_attention_mask=prompt_attention_mask,
@@ -146,4 +146,3 @@ While loading the `text_encoder`, you set `load_in_8bit` to `True`. You could al
 [[autodoc]] PixArtAlphaPipeline
 	- all
 	- __call__
-	

docs/source/en/api/pipelines/pixart_sigma.md

@@ -39,7 +39,7 @@ Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers)
 
 ## Inference with under 8GB GPU VRAM
 
-Run the [`PixArtSigmaPipeline`] with under 8GB GPU VRAM by loading the text encoder in 8-bit precision. Let's walk through a full-fledged example. 
+Run the [`PixArtSigmaPipeline`] with under 8GB GPU VRAM by loading the text encoder in 8-bit precision. Let's walk through a full-fledged example.
 
 First, install the [bitsandbytes](https://github.com/TimDettmers/bitsandbytes) library:
 
@@ -59,7 +59,6 @@ text_encoder = T5EncoderModel.from_pretrained(
     subfolder="text_encoder",
     load_in_8bit=True,
     device_map="auto",
-
 )
 pipe = PixArtSigmaPipeline.from_pretrained(
     "PixArt-alpha/PixArt-Sigma-XL-2-1024-MS",
@@ -77,10 +76,10 @@ with torch.no_grad():
     prompt_embeds, prompt_attention_mask, negative_embeds, negative_prompt_attention_mask = pipe.encode_prompt(prompt)
 ```
 
-Since text embeddings have been computed, remove the `text_encoder` and `pipe` from the memory, and free up som GPU VRAM:
+Since text embeddings have been computed, remove the `text_encoder` and `pipe` from the memory, and free up some GPU VRAM:
 
 ```python
-import gc 
+import gc
 
 def flush():
     gc.collect()
@@ -101,7 +100,7 @@ pipe = PixArtSigmaPipeline.from_pretrained(
 ).to("cuda")
 
 latents = pipe(
-    negative_prompt=None, 
+    negative_prompt=None,
     prompt_embeds=prompt_embeds,
     negative_prompt_embeds=negative_embeds,
     prompt_attention_mask=prompt_attention_mask,
@@ -148,4 +147,3 @@ While loading the `text_encoder`, you set `load_in_8bit` to `True`. You could al
 [[autodoc]] PixArtSigmaPipeline
 	- all
 	- __call__
-	

docs/source/en/using-diffusers/marigold_usage.md

@@ -138,15 +138,15 @@ Because Marigold's latent space is compatible with the base Stable Diffusion, it
 ```diff
   import diffusers
   import torch
-  
+
   pipe = diffusers.MarigoldDepthPipeline.from_pretrained(
       "prs-eth/marigold-depth-lcm-v1-0", variant="fp16", torch_dtype=torch.float16
   ).to("cuda")
-  
+
 + pipe.vae = diffusers.AutoencoderTiny.from_pretrained(
 +     "madebyollin/taesd", torch_dtype=torch.float16
 + ).cuda()
-  
+
   image = diffusers.utils.load_image("https://marigoldmonodepth.github.io/images/einstein.jpg")
   depth = pipe(image)
 ```
@@ -156,13 +156,13 @@ As suggested in [Optimizations](torch2.0), adding `torch.compile` may squeeze ex
 ```diff
   import diffusers
   import torch
-  
+
   pipe = diffusers.MarigoldDepthPipeline.from_pretrained(
       "prs-eth/marigold-depth-lcm-v1-0", variant="fp16", torch_dtype=torch.float16
   ).to("cuda")
-  
+
 + pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
-  
+
   image = diffusers.utils.load_image("https://marigoldmonodepth.github.io/images/einstein.jpg")
   depth = pipe(image)
 ```
@@ -208,7 +208,7 @@ model_paper_kwargs = {
 	diffusers.schedulers.LCMScheduler: {
 		"num_inference_steps": 4,
 		"ensemble_size": 5,
-	},	
+	},
 }
 
 image = diffusers.utils.load_image("https://marigoldmonodepth.github.io/images/einstein.jpg")
@@ -261,7 +261,7 @@ model_paper_kwargs = {
 	diffusers.schedulers.LCMScheduler: {
 		"num_inference_steps": 4,
 		"ensemble_size": 10,
-	},	
+	},
 }
 
 image = diffusers.utils.load_image("https://marigoldmonodepth.github.io/images/einstein.jpg")
@@ -415,7 +415,7 @@ image = diffusers.utils.load_image(
 
 pipe = diffusers.MarigoldDepthPipeline.from_pretrained(
     "prs-eth/marigold-lcm-v1-0", torch_dtype=torch.float16, variant="fp16"
-).to("cuda")
+).to(device)
 
 depth_image = pipe(image, generator=generator).prediction
 depth_image = pipe.image_processor.visualize_depth(depth_image, color_map="binary")
@@ -423,10 +423,10 @@ depth_image[0].save("motorcycle_controlnet_depth.png")
 
 controlnet = diffusers.ControlNetModel.from_pretrained(
     "diffusers/controlnet-depth-sdxl-1.0", torch_dtype=torch.float16, variant="fp16"
-).to("cuda")
+).to(device)
 pipe = diffusers.StableDiffusionXLControlNetPipeline.from_pretrained(
     "SG161222/RealVisXL_V4.0", torch_dtype=torch.float16, variant="fp16", controlnet=controlnet
-).to("cuda")
+).to(device)
 pipe.scheduler = diffusers.DPMSolverMultistepScheduler.from_config(pipe.scheduler.config, use_karras_sigmas=True)
 
 controlnet_out = pipe(

utils/tests_fetcher.py

@@ -692,7 +692,7 @@ def print_tree_deps_of(module, all_edges=None):
 
 def init_test_examples_dependencies() -> Tuple[Dict[str, List[str]], List[str]]:
     """
-    The test examples do not import from the examples (which are just scripts, not modules) so we need som extra
+    The test examples do not import from the examples (which are just scripts, not modules) so we need some extra
     care initializing the dependency map, which is the goal of this function. It initializes the dependency map for
     example files by linking each example to the example test file for the example framework.