make examples in docs device agnostic

docs/source/en/advanced_inference/outpaint.md

@@ -117,7 +117,7 @@ controlnets = [
         "diffusers/controlnet-zoe-depth-sdxl-1.0", dtype=torch.float16
     ),
 ]
-vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", dtype=torch.float16).to("cuda")
+vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", dtype=torch.float16).to("cuda")  # or "mps", "xpu", "cpu"
 pipeline = StableDiffusionXLControlNetPipeline.from_pretrained(
     "SG161222/RealVisXL_V4.0", dtype=torch.float16, variant="fp16", controlnet=controlnets, vae=vae
 ).to("cuda")
@@ -176,7 +176,7 @@ pipeline = StableDiffusionXLInpaintPipeline.from_pretrained(
     dtype=torch.float16,
     variant="fp16",
     vae=vae,
-).to("cuda")
+).to("cuda")  # or "mps", "xpu", "cpu"
 ```
 
 Prepare a mask for the final outpainted image. To create a more natural transition between the original image and the outpainted background, blur the mask to help it blend better.

docs/source/en/api/models/allegro_transformer3d.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import AllegroTransformer3DModel
 
-transformer = AllegroTransformer3DModel.from_pretrained("rhymes-ai/Allegro", subfolder="transformer", dtype=torch.bfloat16).to("cuda")
+transformer = AllegroTransformer3DModel.from_pretrained("rhymes-ai/Allegro", subfolder="transformer", dtype=torch.bfloat16).to("cuda")  # or "mps", "xpu", "cpu"
 ```
 
 ## AllegroTransformer3DModel

docs/source/en/api/models/asymmetricautoencoderkl.md

@@ -41,7 +41,7 @@ mask_image = load_image(mask_url).resize((512, 512))
 
 pipe = StableDiffusionInpaintPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-inpainting")
 pipe.vae = AsymmetricAutoencoderKL.from_pretrained("cross-attention/asymmetric-autoencoder-kl-x-1-5")
-pipe.to("cuda")
+pipe.to("cuda")  # or "mps", "xpu", "cpu"
 
 image = pipe(prompt=prompt, image=original_image, mask_image=mask_image).images[0]
 make_image_grid([original_image, mask_image, image], rows=1, cols=3)

docs/source/en/api/models/autoencoder_dc.md

@@ -36,7 +36,7 @@ Load a model in Diffusers format with [`~ModelMixin.from_pretrained`].
 ```python
 from diffusers import AutoencoderDC
 
-ae = AutoencoderDC.from_pretrained("mit-han-lab/dc-ae-f32c32-sana-1.0-diffusers", dtype=torch.float32).to("cuda")
+ae = AutoencoderDC.from_pretrained("mit-han-lab/dc-ae-f32c32-sana-1.0-diffusers", dtype=torch.float32).to("cuda")  # or "mps", "xpu", "cpu"
 ```
 
 ## Load a model in Diffusers via `from_single_file`

docs/source/en/api/models/autoencoder_rae.md

@@ -34,7 +34,7 @@ from diffusers import AutoencoderRAE
 
 model = AutoencoderRAE.from_pretrained(
     "nyu-visionx/RAE-dinov2-wReg-base-ViTXL-n08"
-).to("cuda").eval()
+).to("cuda").eval()  # or "mps", "xpu", "cpu"
 ```
 
 ## Encoding and decoding a real image
@@ -47,7 +47,7 @@ from torchvision.transforms.functional import to_tensor, to_pil_image
 
 model = AutoencoderRAE.from_pretrained(
     "nyu-visionx/RAE-dinov2-wReg-base-ViTXL-n08"
-).to("cuda").eval()
+).to("cuda").eval()  # or "mps", "xpu", "cpu"
 
 image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")
 image = image.convert("RGB").resize((224, 224))
@@ -68,7 +68,7 @@ Some pretrained checkpoints include per-channel `latents_mean` and `latents_std`
 ```python
 model = AutoencoderRAE.from_pretrained(
     "nyu-visionx/RAE-dinov2-wReg-base-ViTXL-n08"
-).to("cuda").eval()
+).to("cuda").eval()  # or "mps", "xpu", "cpu"
 
 # Latent normalization is handled automatically inside encode/decode
 # when the checkpoint config includes latents_mean/latents_std.

docs/source/en/api/models/autoencoder_tiny.md

@@ -24,7 +24,7 @@ pipe = DiffusionPipeline.from_pretrained(
     "stabilityai/stable-diffusion-2-1-base", dtype=torch.float16
 )
 pipe.vae = AutoencoderTiny.from_pretrained("madebyollin/taesd", dtype=torch.float16)
-pipe = pipe.to("cuda")
+pipe = pipe.to("cuda")  # or "mps", "xpu", "cpu"
 
 prompt = "slice of delicious New York-style berry cheesecake"
 image = pipe(prompt, num_inference_steps=25).images[0]
@@ -41,7 +41,7 @@ pipe = DiffusionPipeline.from_pretrained(
     "stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.float16
 )
 pipe.vae = AutoencoderTiny.from_pretrained("madebyollin/taesdxl", dtype=torch.float16)
-pipe = pipe.to("cuda")
+pipe = pipe.to("cuda")  # or "mps", "xpu", "cpu"
 
 prompt = "slice of delicious New York-style berry cheesecake"
 image = pipe(prompt, num_inference_steps=25).images[0]

docs/source/en/api/models/autoencoderkl_allegro.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import AutoencoderKLAllegro
 
-vae = AutoencoderKLAllegro.from_pretrained("rhymes-ai/Allegro", subfolder="vae", dtype=torch.float32).to("cuda")
+vae = AutoencoderKLAllegro.from_pretrained("rhymes-ai/Allegro", subfolder="vae", dtype=torch.float32).to("cuda")  # or "mps", "xpu", "cpu"
 ```
 
 ## AutoencoderKLAllegro

docs/source/en/api/models/autoencoderkl_audio_ltx_2.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import AutoencoderKLLTX2Audio
 
-vae = AutoencoderKLLTX2Audio.from_pretrained("Lightricks/LTX-2", subfolder="vae", dtype=torch.float32).to("cuda")
+vae = AutoencoderKLLTX2Audio.from_pretrained("Lightricks/LTX-2", subfolder="vae", dtype=torch.float32).to("cuda")  # or "mps", "xpu", "cpu"
 ```
 
 ## AutoencoderKLLTX2Audio

docs/source/en/api/models/autoencoderkl_cogvideox.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import AutoencoderKLCogVideoX
 
-vae = AutoencoderKLCogVideoX.from_pretrained("THUDM/CogVideoX-2b", subfolder="vae", dtype=torch.float16).to("cuda")
+vae = AutoencoderKLCogVideoX.from_pretrained("THUDM/CogVideoX-2b", subfolder="vae", dtype=torch.float16).to("cuda")  # or "mps", "xpu", "cpu"
 ```
 
 ## AutoencoderKLCogVideoX

docs/source/en/api/models/autoencoderkl_ltx_2.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import AutoencoderKLLTX2Video
 
-vae = AutoencoderKLLTX2Video.from_pretrained("Lightricks/LTX-2", subfolder="vae", dtype=torch.float32).to("cuda")
+vae = AutoencoderKLLTX2Video.from_pretrained("Lightricks/LTX-2", subfolder="vae", dtype=torch.float32).to("cuda")  # or "mps", "xpu", "cpu"
 ```
 
 ## AutoencoderKLLTX2Video

docs/source/en/api/models/autoencoderkl_ltx_video.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import AutoencoderKLLTXVideo
 
-vae = AutoencoderKLLTXVideo.from_pretrained("Lightricks/LTX-Video", subfolder="vae", dtype=torch.float32).to("cuda")
+vae = AutoencoderKLLTXVideo.from_pretrained("Lightricks/LTX-Video", subfolder="vae", dtype=torch.float32).to("cuda")  # or "mps", "xpu", "cpu"
 ```
 
 ## AutoencoderKLLTXVideo

docs/source/en/api/models/autoencoderkl_magvit.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import AutoencoderKLMagvit
 
-vae = AutoencoderKLMagvit.from_pretrained("alibaba-pai/EasyAnimateV5.1-12b-zh", subfolder="vae", dtype=torch.float16).to("cuda")
+vae = AutoencoderKLMagvit.from_pretrained("alibaba-pai/EasyAnimateV5.1-12b-zh", subfolder="vae", dtype=torch.float16).to("cuda")  # or "mps", "xpu", "cpu"
 ```
 
 ## AutoencoderKLMagvit

docs/source/en/api/models/autoencoderkl_minimax_h3.md

@@ -27,7 +27,7 @@ from diffusers import AutoencoderKLMiniMaxH3
 
 vae = AutoencoderKLMiniMaxH3.from_pretrained(
     "MiniMaxAI/MiniMax-H3", subfolder="vae", dtype=torch.float32
-).to("cuda")
+).to("cuda")  # or "mps", "xpu", "cpu"
 ```
 
 ## AutoencoderKLMiniMaxH3

docs/source/en/api/models/autoencoderkl_minimax_h3_audio.md

@@ -25,7 +25,7 @@ from diffusers import AutoencoderKLMiniMaxH3Audio
 
 audio_vae = AutoencoderKLMiniMaxH3Audio.from_pretrained(
     "MiniMaxAI/MiniMax-H3", subfolder="audio_vae", dtype=torch.float32
-).to("cuda")
+).to("cuda")  # or "mps", "xpu", "cpu"
 ```
 
 ## AutoencoderKLMiniMaxH3Audio

docs/source/en/api/models/autoencoderkl_mochi.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import AutoencoderKLMochi
 
-vae = AutoencoderKLMochi.from_pretrained("genmo/mochi-1-preview", subfolder="vae", dtype=torch.float32).to("cuda")
+vae = AutoencoderKLMochi.from_pretrained("genmo/mochi-1-preview", subfolder="vae", dtype=torch.float32).to("cuda")  # or "mps", "xpu", "cpu"
 ```
 
 ## AutoencoderKLMochi

docs/source/en/api/models/cogvideox_transformer3d.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import CogVideoXTransformer3DModel
 
-transformer = CogVideoXTransformer3DModel.from_pretrained("THUDM/CogVideoX-2b", subfolder="transformer", dtype=torch.float16).to("cuda")
+transformer = CogVideoXTransformer3DModel.from_pretrained("THUDM/CogVideoX-2b", subfolder="transformer", dtype=torch.float16).to("cuda")  # or "mps", "xpu", "cpu"
 ```
 
 ## CogVideoXTransformer3DModel

docs/source/en/api/models/cogview3plus_transformer2d.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import CogView3PlusTransformer2DModel
 
-transformer = CogView3PlusTransformer2DModel.from_pretrained("THUDM/CogView3Plus-3b", subfolder="transformer", dtype=torch.bfloat16).to("cuda")
+transformer = CogView3PlusTransformer2DModel.from_pretrained("THUDM/CogView3Plus-3b", subfolder="transformer", dtype=torch.bfloat16).to("cuda")  # or "mps", "xpu", "cpu"
 ```
 
 ## CogView3PlusTransformer2DModel

docs/source/en/api/models/cogview4_transformer2d.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import CogView4Transformer2DModel
 
-transformer = CogView4Transformer2DModel.from_pretrained("THUDM/CogView4-6B", subfolder="transformer", dtype=torch.bfloat16).to("cuda")
+transformer = CogView4Transformer2DModel.from_pretrained("THUDM/CogView4-6B", subfolder="transformer", dtype=torch.bfloat16).to("cuda")  # or "mps", "xpu", "cpu"
 ```
 
 ## CogView4Transformer2DModel

docs/source/en/api/models/consisid_transformer3d.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import ConsisIDTransformer3DModel
 
-transformer = ConsisIDTransformer3DModel.from_pretrained("BestWishYsh/ConsisID-preview", subfolder="transformer", dtype=torch.bfloat16).to("cuda")
+transformer = ConsisIDTransformer3DModel.from_pretrained("BestWishYsh/ConsisID-preview", subfolder="transformer", dtype=torch.bfloat16).to("cuda")  # or "mps", "xpu", "cpu"
 ```
 
 ## ConsisIDTransformer3DModel

docs/source/en/api/models/controlnet.md

@@ -43,7 +43,7 @@ from diffusers import ControlNetModel, UNet2DConditionModel
 lora_id = "stabilityai/control-lora"
 lora_filename = "control-LoRAs-rank128/control-lora-canny-rank128.safetensors"
 
-unet = UNet2DConditionModel.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", subfolder="unet", dtype=torch.bfloat16).to("cuda")
+unet = UNet2DConditionModel.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", subfolder="unet", dtype=torch.bfloat16).to("cuda")  # or "mps", "xpu", "cpu"
 controlnet = ControlNetModel.from_unet(unet).to(device="cuda", dtype=torch.bfloat16)
 controlnet.load_lora_adapter(lora_id, weight_name=lora_filename, prefix=None, controlnet_config=controlnet.config)
 ```

docs/source/en/api/models/easyanimate_transformer3d.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import EasyAnimateTransformer3DModel
 
-transformer = EasyAnimateTransformer3DModel.from_pretrained("alibaba-pai/EasyAnimateV5.1-12b-zh", subfolder="transformer", dtype=torch.float16).to("cuda")
+transformer = EasyAnimateTransformer3DModel.from_pretrained("alibaba-pai/EasyAnimateV5.1-12b-zh", subfolder="transformer", dtype=torch.float16).to("cuda")  # or "mps", "xpu", "cpu"
 ```
 
 ## EasyAnimateTransformer3DModel

docs/source/en/api/models/ltx2_diffusion_decoder.md

@@ -23,7 +23,7 @@ pipeline's `vae`: run any LTX-2 pipeline with `output_type="latent"`, then decod
 import torch
 from diffusers import LTX2Pipeline, LTX2VideoDiffusionDecodePipeline, LTX2VideoDiffusionDecoderModel
 
-pipe = LTX2Pipeline.from_pretrained("Lightricks/LTX-2.5-Diffusers", dtype=torch.bfloat16).to("cuda")
+pipe = LTX2Pipeline.from_pretrained("Lightricks/LTX-2.5-Diffusers", dtype=torch.bfloat16).to("cuda")  # or "mps", "xpu", "cpu"
 latents = pipe(prompt="a potter shaping a clay vase", output_type="latent").frames
 
 decoder = LTX2VideoDiffusionDecoderModel.from_pretrained(

docs/source/en/api/models/ltx2_video_transformer3d.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import LTX2VideoTransformer3DModel
 
-transformer = LTX2VideoTransformer3DModel.from_pretrained("Lightricks/LTX-2", subfolder="transformer", dtype=torch.bfloat16).to("cuda")
+transformer = LTX2VideoTransformer3DModel.from_pretrained("Lightricks/LTX-2", subfolder="transformer", dtype=torch.bfloat16).to("cuda")  # or "mps", "xpu", "cpu"
 ```
 
 ## LTX2VideoTransformer3DModel

docs/source/en/api/models/ltx_video_transformer3d.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import LTXVideoTransformer3DModel
 
-transformer = LTXVideoTransformer3DModel.from_pretrained("Lightricks/LTX-Video", subfolder="transformer", dtype=torch.bfloat16).to("cuda")
+transformer = LTXVideoTransformer3DModel.from_pretrained("Lightricks/LTX-Video", subfolder="transformer", dtype=torch.bfloat16).to("cuda")  # or "mps", "xpu", "cpu"
 ```
 
 ## LTXVideoTransformer3DModel

docs/source/en/api/models/minimax_h3_transformer3d.md

@@ -27,7 +27,7 @@ from diffusers import MiniMaxH3Transformer3DModel
 
 transformer = MiniMaxH3Transformer3DModel.from_pretrained(
     "MiniMaxAI/MiniMax-H3", subfolder="transformer", dtype=torch.bfloat16
-).to("cuda")
+).to("cuda")  # or "mps", "xpu", "cpu"
 ```
 
 The checkpoint is mixed precision: the two input patch projections, the timestep MLP and the two output heads are float32 while the block stack is bfloat16. `from_pretrained` keeps that layout through `_keep_in_fp32_modules`, so pass `dtype=torch.bfloat16` and let it place the float32 modules rather than casting the model with `.to(torch.bfloat16)` afterwards.

docs/source/en/api/models/mochi_transformer3d.md

@@ -18,7 +18,7 @@ The model can be loaded with the following code snippet.
 ```python
 from diffusers import MochiTransformer3DModel
 
-transformer = MochiTransformer3DModel.from_pretrained("genmo/mochi-1-preview", subfolder="transformer", dtype=torch.float16).to("cuda")
+transformer = MochiTransformer3DModel.from_pretrained("genmo/mochi-1-preview", subfolder="transformer", dtype=torch.float16).to("cuda")  # or "mps", "xpu", "cpu"
 ```
 
 ## MochiTransformer3DModel

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

@@ -55,7 +55,7 @@ import soundfile as sf
 from diffusers import AceStepPipeline
 
 pipe = AceStepPipeline.from_pretrained("ACE-Step/acestep-v15-xl-turbo-diffusers", dtype=torch.bfloat16)
-pipe = pipe.to("cuda")
+pipe = pipe.to("cuda")  # or "mps", "xpu", "cpu"
 
 audio = pipe(
     prompt="A beautiful piano piece with soft melodies and gentle rhythm",

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

@@ -22,7 +22,7 @@ from diffusers import ModularPipeline
 
 pipe = ModularPipeline.from_pretrained("circlestone-labs/Anima-Base-v1.0-Diffusers")
 pipe.load_components(dtype=torch.bfloat16)
-pipe.to("cuda")
+pipe.to("cuda")  # or "mps", "xpu", "cpu"
 
 image = pipe(prompt="masterpiece, best quality, 1girl, solo, city lights").images[0]
 ```

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

@@ -131,7 +131,7 @@ pipe: AnimateDiffControlNetPipeline = AnimateDiffControlNetPipeline.from_pretrai
     motion_adapter=motion_adapter,
     controlnet=controlnet,
     vae=vae,
-).to(device="cuda", dtype=torch.float16)
+).to(device="cuda", dtype=torch.float16)  # or "mps", "xpu", "cpu"
 pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config, beta_schedule="linear")
 pipe.load_lora_weights("wangfuyun/AnimateLCM", weight_name="AnimateLCM_sd15_t2v_lora.safetensors", adapter_name="lcm-lora")
 pipe.set_adapters(["lcm-lora"], [0.8])
@@ -211,7 +211,7 @@ motion_adapter_id = "guoyww/animatediff-motion-adapter-v1-5-3"
 controlnet_id = "guoyww/animatediff-sparsectrl-scribble"
 lora_adapter_id = "guoyww/animatediff-motion-lora-v1-5-3"
 vae_id = "stabilityai/sd-vae-ft-mse"
-device = "cuda"
+device = "cuda"  # or "mps", "xpu", "cpu"
 
 motion_adapter = MotionAdapter.from_pretrained(motion_adapter_id, dtype=torch.float16).to(device)
 controlnet = SparseControlNetModel.from_pretrained(controlnet_id, dtype=torch.float16).to(device)
@@ -307,7 +307,7 @@ motion_adapter_id = "guoyww/animatediff-motion-adapter-v1-5-3"
 controlnet_id = "guoyww/animatediff-sparsectrl-rgb"
 lora_adapter_id = "guoyww/animatediff-motion-lora-v1-5-3"
 vae_id = "stabilityai/sd-vae-ft-mse"
-device = "cuda"
+device = "cuda"  # or "mps", "xpu", "cpu"
 
 motion_adapter = MotionAdapter.from_pretrained(motion_adapter_id, dtype=torch.float16).to(device)
 controlnet = SparseControlNetModel.from_pretrained(controlnet_id, dtype=torch.float16).to(device)
@@ -392,7 +392,7 @@ pipe = AnimateDiffSDXLPipeline.from_pretrained(
     scheduler=scheduler,
     dtype=torch.float16,
     variant="fp16",
-).to("cuda")
+).to("cuda")  # or "mps", "xpu", "cpu"
 
 # enable memory savings
 pipe.vae.enable_slicing()
@@ -549,7 +549,7 @@ pipe = AnimateDiffVideoToVideoControlNetPipeline.from_pretrained(
     motion_adapter=motion_adapter,
     controlnet=controlnet,
     vae=vae,
-).to(device="cuda", dtype=torch.float16)
+).to(device="cuda", dtype=torch.float16)  # or "mps", "xpu", "cpu"
 
 # Enable LCM to speed up inference
 pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config, beta_schedule="linear")
@@ -761,7 +761,7 @@ from diffusers.utils import export_to_gif
 
 adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-v1-5-2")
 model_id = "SG161222/Realistic_Vision_V5.1_noVAE"
-pipe = AnimateDiffPipeline.from_pretrained(model_id, motion_adapter=adapter, dtype=torch.float16).to("cuda")
+pipe = AnimateDiffPipeline.from_pretrained(model_id, motion_adapter=adapter, dtype=torch.float16).to("cuda")  # or "mps", "xpu", "cpu"
 pipe.scheduler = DDIMScheduler.from_pretrained(
     model_id,
     subfolder="scheduler",
@@ -951,7 +951,7 @@ pipe.set_adapters(["lcm_lora"], [0.8])
 
 # Enable FreeNoise for long prompt generation
 pipe.enable_free_noise(context_length=16, context_stride=4)
-pipe.to("cuda")
+pipe.to("cuda")  # or "mps", "xpu", "cpu"
 
 # Can be a single prompt, or a dictionary with frame timesteps
 prompt = {

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

@@ -49,7 +49,7 @@ from diffusers.utils import export_to_video
 
 pipe = AnyFlowPipeline.from_pretrained(
     "nvidia/AnyFlow-Wan2.1-T2V-1.3B-Diffusers", dtype=torch.bfloat16
-).to("cuda")
+).to("cuda")  # or "mps", "xpu", "cpu"
 
 prompt = (
     "An astronaut runs smoothly and appears almost weightless on the lunar surface, "
@@ -85,7 +85,7 @@ from diffusers.utils import export_to_video
 
 pipe = AnyFlowFARPipeline.from_pretrained(
     "nvidia/AnyFlow-FAR-Wan2.1-1.3B-Diffusers", dtype=torch.bfloat16
-).to("cuda")
+).to("cuda")  # or "mps", "xpu", "cpu"
 
 prompt = (
     "An astronaut runs smoothly and appears almost weightless on the lunar surface, "
@@ -106,7 +106,7 @@ from diffusers.utils import export_to_video, load_image
 
 pipe = AnyFlowFARPipeline.from_pretrained(
     "nvidia/AnyFlow-FAR-Wan2.1-1.3B-Diffusers", dtype=torch.bfloat16
-).to("cuda")
+).to("cuda")  # or "mps", "xpu", "cpu"
 
 # Example conditioning image from the AnyFlow repo.
 first_frame = load_image(
@@ -140,7 +140,7 @@ from diffusers.utils import export_to_video, load_video
 
 pipe = AnyFlowFARPipeline.from_pretrained(
     "nvidia/AnyFlow-FAR-Wan2.1-1.3B-Diffusers", dtype=torch.bfloat16
-).to("cuda")
+).to("cuda")  # or "mps", "xpu", "cpu"
 
 # Example conditioning clip from the AnyFlow repo — take the first 9 frames (3 latent frames at VAE temporal stride 4).
 context_frames = load_video(