Migrate qwenimage pipeline docstrings from torch_dtype to dtype

docs/source/en/quantization/torchao.md

@@ -45,7 +45,7 @@ pipeline = DiffusionPipeline.from_pretrained(
 pipeline = DiffusionPipeline.from_pretrained(
     "black-forest-labs/FLUX.1-dev",
     quantization_config=pipeline_quant_config,
-    torch_dtype=torch.bfloat16,
+    dtype=torch.bfloat16,
 )
 pipeline.to("cuda")
 ```

src/diffusers/pipelines/README.md

@@ -113,7 +113,7 @@ from diffusers import StableDiffusionImg2ImgPipeline
 device = "cuda"
 pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
     "stable-diffusion-v1-5/stable-diffusion-v1-5",
-    torch_dtype=torch.float16,
+    dtype=torch.float16,
 ).to(device)
 
 # let's download an initial image
@@ -160,7 +160,7 @@ mask_image = download_image(mask_url).resize((512, 512))
 
 pipe = StableDiffusionInpaintPipeline.from_pretrained(
     "stable-diffusion-v1-5/stable-diffusion-inpainting",
-    torch_dtype=torch.float16,
+    dtype=torch.float16,
 )
 pipe = pipe.to("cuda")
 

src/diffusers/pipelines/ace_step/pipeline_ace_step.py

@@ -86,7 +86,7 @@ def _normalize_audio_codes(audio_codes: Union[str, List[str]], batch_size: int)
         >>> from diffusers import AceStepPipeline
 
         >>> pipe = AceStepPipeline.from_pretrained(
-        ...     "ACE-Step/acestep-v15-xl-turbo-diffusers", torch_dtype=torch.bfloat16
+        ...     "ACE-Step/acestep-v15-xl-turbo-diffusers", dtype=torch.bfloat16
         ... )
         >>> pipe = pipe.to("cuda")
 

src/diffusers/pipelines/allegro/pipeline_allegro.py

@@ -66,8 +66,8 @@
         >>> from diffusers import AutoencoderKLAllegro, AllegroPipeline
         >>> from diffusers.utils import export_to_video
 
-        >>> vae = AutoencoderKLAllegro.from_pretrained("rhymes-ai/Allegro", subfolder="vae", torch_dtype=torch.float32)
-        >>> pipe = AllegroPipeline.from_pretrained("rhymes-ai/Allegro", vae=vae, torch_dtype=torch.bfloat16).to("cuda")
+        >>> vae = AutoencoderKLAllegro.from_pretrained("rhymes-ai/Allegro", subfolder="vae", dtype=torch.float32)
+        >>> pipe = AllegroPipeline.from_pretrained("rhymes-ai/Allegro", vae=vae, dtype=torch.bfloat16).to("cuda")
         >>> pipe.vae.enable_tiling()
 
         >>> prompt = (

src/diffusers/pipelines/animatediff/pipeline_animatediff_controlnet.py

@@ -70,12 +70,12 @@
 
         >>> # Download controlnets from https://huggingface.co/lllyasviel/ControlNet-v1-1 to use .from_single_file
         >>> # Download Diffusers-format controlnets, such as https://huggingface.co/lllyasviel/sd-controlnet-depth, to use .from_pretrained()
-        >>> controlnet = ControlNetModel.from_single_file("control_v11f1p_sd15_depth.pth", torch_dtype=torch.float16)
+        >>> controlnet = ControlNetModel.from_single_file("control_v11f1p_sd15_depth.pth", dtype=torch.float16)
 
         >>> # We use AnimateLCM for this example but one can use the original motion adapters as well (for example, https://huggingface.co/guoyww/animatediff-motion-adapter-v1-5-3)
         >>> motion_adapter = MotionAdapter.from_pretrained("wangfuyun/AnimateLCM")
 
-        >>> vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-mse", torch_dtype=torch.float16)
+        >>> vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-mse", dtype=torch.float16)
         >>> pipe: AnimateDiffControlNetPipeline = AnimateDiffControlNetPipeline.from_pretrained(
         ...     "SG161222/Realistic_Vision_V5.1_noVAE",
         ...     motion_adapter=motion_adapter,

src/diffusers/pipelines/animatediff/pipeline_animatediff_sdxl.py

@@ -80,7 +80,7 @@
         >>> from diffusers.utils import export_to_gif
 
         >>> adapter = MotionAdapter.from_pretrained(
-        ...     "a-r-r-o-w/animatediff-motion-adapter-sdxl-beta", torch_dtype=torch.float16
+        ...     "a-r-r-o-w/animatediff-motion-adapter-sdxl-beta", dtype=torch.float16
         ... )
 
         >>> model_id = "stabilityai/stable-diffusion-xl-base-1.0"
@@ -96,7 +96,7 @@
         ...     model_id,
         ...     motion_adapter=adapter,
         ...     scheduler=scheduler,
-        ...     torch_dtype=torch.float16,
+        ...     dtype=torch.float16,
         ...     variant="fp16",
         ... ).to("cuda")
 

src/diffusers/pipelines/animatediff/pipeline_animatediff_sparsectrl.py

@@ -69,9 +69,9 @@
         >>> vae_id = "stabilityai/sd-vae-ft-mse"
         >>> device = "cuda"
 
-        >>> motion_adapter = MotionAdapter.from_pretrained(motion_adapter_id, torch_dtype=torch.float16).to(device)
-        >>> controlnet = SparseControlNetModel.from_pretrained(controlnet_id, torch_dtype=torch.float16).to(device)
-        >>> vae = AutoencoderKL.from_pretrained(vae_id, torch_dtype=torch.float16).to(device)
+        >>> motion_adapter = MotionAdapter.from_pretrained(motion_adapter_id, dtype=torch.float16).to(device)
+        >>> controlnet = SparseControlNetModel.from_pretrained(controlnet_id, dtype=torch.float16).to(device)
+        >>> vae = AutoencoderKL.from_pretrained(vae_id, dtype=torch.float16).to(device)
         >>> scheduler = DPMSolverMultistepScheduler.from_pretrained(
         ...     model_id,
         ...     subfolder="scheduler",
@@ -85,7 +85,7 @@
         ...     controlnet=controlnet,
         ...     vae=vae,
         ...     scheduler=scheduler,
-        ...     torch_dtype=torch.float16,
+        ...     dtype=torch.float16,
         ... ).to(device)
         >>> pipe.load_lora_weights(lora_adapter_id, adapter_name="motion_lora")
         >>> pipe.fuse_lora(lora_scale=1.0)

src/diffusers/pipelines/animatediff/pipeline_animatediff_video2video.py

@@ -62,7 +62,7 @@
         >>> from PIL import Image
 
         >>> adapter = MotionAdapter.from_pretrained(
-        ...     "guoyww/animatediff-motion-adapter-v1-5-2", torch_dtype=torch.float16
+        ...     "guoyww/animatediff-motion-adapter-v1-5-2", dtype=torch.float16
         ... )
         >>> pipe = AnimateDiffVideoToVideoPipeline.from_pretrained(
         ...     "SG161222/Realistic_Vision_V5.1_noVAE", motion_adapter=adapter

src/diffusers/pipelines/animatediff/pipeline_animatediff_video2video_controlnet.py

@@ -70,10 +70,10 @@
         >>> from diffusers import AutoencoderKL, ControlNetModel, MotionAdapter, LCMScheduler
 
         >>> controlnet = ControlNetModel.from_pretrained(
-        ...     "lllyasviel/sd-controlnet-openpose", torch_dtype=torch.float16
+        ...     "lllyasviel/sd-controlnet-openpose", dtype=torch.float16
         ... )
         >>> motion_adapter = MotionAdapter.from_pretrained("wangfuyun/AnimateLCM")
-        >>> vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-mse", torch_dtype=torch.float16)
+        >>> vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-mse", dtype=torch.float16)
 
         >>> pipe = AnimateDiffVideoToVideoControlNetPipeline.from_pretrained(
         ...     "SG161222/Realistic_Vision_V5.1_noVAE",

src/diffusers/pipelines/anyflow/pipeline_anyflow.py

@@ -46,7 +46,7 @@
         >>> from diffusers.utils import export_to_video
 
         >>> pipe = AnyFlowPipeline.from_pretrained(
-        ...     "nvidia/AnyFlow-Wan2.1-T2V-14B-Diffusers", torch_dtype=torch.bfloat16
+        ...     "nvidia/AnyFlow-Wan2.1-T2V-14B-Diffusers", dtype=torch.bfloat16
         ... ).to("cuda")
 
         >>> prompt = "A red panda eating bamboo in a forest, cinematic lighting"

src/diffusers/pipelines/anyflow/pipeline_anyflow_far.py

@@ -49,7 +49,7 @@
         >>> from diffusers.utils import export_to_video, load_image
 
         >>> pipe = AnyFlowFARPipeline.from_pretrained(
-        ...     "nvidia/AnyFlow-FAR-Wan2.1-1.3B-Diffusers", torch_dtype=torch.bfloat16
+        ...     "nvidia/AnyFlow-FAR-Wan2.1-1.3B-Diffusers", dtype=torch.bfloat16
         ... ).to("cuda")
 
         >>> # Single-frame I2V: wrap the conditioning image as a (1, 1, 3, H, W) tensor in [0, 1].

src/diffusers/pipelines/audioldm2/pipeline_audioldm2.py

@@ -71,7 +71,7 @@
         >>> from diffusers import AudioLDM2Pipeline
 
         >>> repo_id = "cvssp/audioldm2"
-        >>> pipe = AudioLDM2Pipeline.from_pretrained(repo_id, torch_dtype=torch.float16)
+        >>> pipe = AudioLDM2Pipeline.from_pretrained(repo_id, dtype=torch.float16)
         >>> pipe = pipe.to("cuda")
 
         >>> # define the prompts
@@ -101,7 +101,7 @@
         >>> from diffusers import AudioLDM2Pipeline
 
         >>> repo_id = "anhnct/audioldm2_gigaspeech"
-        >>> pipe = AudioLDM2Pipeline.from_pretrained(repo_id, torch_dtype=torch.float16)
+        >>> pipe = AudioLDM2Pipeline.from_pretrained(repo_id, dtype=torch.float16)
         >>> pipe = pipe.to("cuda")
 
         >>> # define the prompts
@@ -398,7 +398,7 @@ def encode_prompt(
         >>> from diffusers import AudioLDM2Pipeline
 
         >>> repo_id = "cvssp/audioldm2"
-        >>> pipe = AudioLDM2Pipeline.from_pretrained(repo_id, torch_dtype=torch.float16)
+        >>> pipe = AudioLDM2Pipeline.from_pretrained(repo_id, dtype=torch.float16)
         >>> pipe = pipe.to("cuda")
 
         >>> # Get text embedding vectors

src/diffusers/pipelines/aura_flow/pipeline_aura_flow.py

@@ -51,7 +51,7 @@
         >>> import torch
         >>> from diffusers import AuraFlowPipeline
 
-        >>> pipe = AuraFlowPipeline.from_pretrained("fal/AuraFlow", torch_dtype=torch.float16)
+        >>> pipe = AuraFlowPipeline.from_pretrained("fal/AuraFlow", dtype=torch.float16)
         >>> pipe = pipe.to("cuda")
         >>> prompt = "A cat holding a sign that says hello world"
         >>> image = pipe(prompt).images[0]

src/diffusers/pipelines/auto_pipeline.py

@@ -1384,7 +1384,7 @@ def from_pretrained(cls, pretrained_model_or_path, **kwargs):
         >>> from diffusers import AutoPipelineForText2Audio
 
         >>> pipeline = AutoPipelineForText2Audio.from_pretrained(
-        ...     "stabilityai/stable-audio-open-1.0", torch_dtype=torch.float16
+        ...     "stabilityai/stable-audio-open-1.0", dtype=torch.float16
         ... )
         >>> pipeline = pipeline.to("cuda")
 
@@ -1443,7 +1443,7 @@ def from_pipe(cls, pipeline, **kwargs):
         >>> import soundfile as sf
         >>> from diffusers import AutoPipelineForText2Audio, StableAudioPipeline
 
-        >>> pipe = StableAudioPipeline.from_pretrained("stabilityai/stable-audio-open-1.0", torch_dtype=torch.float16)
+        >>> pipe = StableAudioPipeline.from_pretrained("stabilityai/stable-audio-open-1.0", dtype=torch.float16)
 
         >>> pipe_audio = AutoPipelineForText2Audio.from_pipe(pipe)
         >>> output = pipe_audio(

src/diffusers/pipelines/bria/pipeline_bria.py

@@ -49,7 +49,7 @@
         >>> import torch
         >>> from diffusers import BriaPipeline
 
-        >>> pipe = BriaPipeline.from_pretrained("briaai/BRIA-3.2", torch_dtype=torch.bfloat16)
+        >>> pipe = BriaPipeline.from_pretrained("briaai/BRIA-3.2", dtype=torch.bfloat16)
         >>> pipe.to("cuda")
         # BRIA's T5 text encoder is sensitive to precision. We need to cast it to bfloat16 and keep the final layer in float32.
 

src/diffusers/pipelines/bria_fibo/pipeline_bria_fibo.py

@@ -57,7 +57,7 @@
     pipe = BriaFiboPipeline.from_pretrained(
         "briaai/FIBO",
         trust_remote_code=True,
-        torch_dtype=torch.bfloat16,
+        dtype=torch.bfloat16,
     )
     pipe.enable_model_cpu_offload()
 

src/diffusers/pipelines/bria_fibo/pipeline_bria_fibo_edit.py

@@ -64,7 +64,7 @@
 
     pipe = BriaFiboEditPipeline.from_pretrained(
         "briaai/fibo-edit",
-        torch_dtype=torch.bfloat16,
+        dtype=torch.bfloat16,
     )
     pipe.to("cuda")
 

src/diffusers/pipelines/chroma/pipeline_chroma.py

@@ -54,11 +54,11 @@
 
         >>> model_id = "lodestones/Chroma1-HD"
         >>> ckpt_path = "https://huggingface.co/lodestones/Chroma1-HD/blob/main/Chroma1-HD.safetensors"
-        >>> transformer = ChromaTransformer2DModel.from_single_file(ckpt_path, torch_dtype=torch.bfloat16)
+        >>> transformer = ChromaTransformer2DModel.from_single_file(ckpt_path, dtype=torch.bfloat16)
         >>> pipe = ChromaPipeline.from_pretrained(
         ...     model_id,
         ...     transformer=transformer,
-        ...     torch_dtype=torch.bfloat16,
+        ...     dtype=torch.bfloat16,
         ... )
         >>> pipe.enable_model_cpu_offload()
         >>> prompt = [

src/diffusers/pipelines/chroma/pipeline_chroma_img2img.py

@@ -57,7 +57,7 @@
         >>> pipe = ChromaImg2ImgPipeline.from_pretrained(
         ...     model_id,
         ...     transformer=transformer,
-        ...     torch_dtype=torch.bfloat16,
+        ...     dtype=torch.bfloat16,
         ... )
         >>> pipe.enable_model_cpu_offload()
         >>> init_image = load_image(

src/diffusers/pipelines/chroma/pipeline_chroma_inpainting.py

@@ -65,7 +65,7 @@
         >>> from diffusers import ChromaInpaintPipeline
         >>> from diffusers.utils import load_image
 
-        >>> pipe = ChromaInpaintPipeline.from_pretrained("lodestones/Chroma1-HD", torch_dtype=torch.bfloat16)
+        >>> pipe = ChromaInpaintPipeline.from_pretrained("lodestones/Chroma1-HD", dtype=torch.bfloat16)
         >>> pipe.to("cuda")
         >>> prompt = "Face of a yellow cat, high resolution, sitting on a park bench"
         >>> img_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png"

src/diffusers/pipelines/chronoedit/pipeline_chronoedit.py

@@ -56,14 +56,14 @@
         >>> # Available models: nvidia/ChronoEdit-14B-Diffusers
         >>> model_id = "nvidia/ChronoEdit-14B-Diffusers"
         >>> image_encoder = CLIPVisionModel.from_pretrained(
-        ...     model_id, subfolder="image_encoder", torch_dtype=torch.float32
+        ...     model_id, subfolder="image_encoder", dtype=torch.float32
         ... )
-        >>> vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
+        >>> vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", dtype=torch.float32)
         >>> transformer = ChronoEditTransformer3DModel.from_pretrained(
-        ...     model_id, subfolder="transformer", torch_dtype=torch.bfloat16
+        ...     model_id, subfolder="transformer", dtype=torch.bfloat16
         ... )
         >>> pipe = ChronoEditPipeline.from_pretrained(
-        ...     model_id, vae=vae, image_encoder=image_encoder, transformer=transformer, torch_dtype=torch.bfloat16
+        ...     model_id, vae=vae, image_encoder=image_encoder, transformer=transformer, dtype=torch.bfloat16
         ... )
         >>> pipe.to("cuda")
 

src/diffusers/pipelines/cogvideo/pipeline_cogvideox.py

@@ -50,7 +50,7 @@
         >>> from diffusers.utils import export_to_video
 
         >>> # Models: "THUDM/CogVideoX-2b" or "THUDM/CogVideoX-5b"
-        >>> pipe = CogVideoXPipeline.from_pretrained("THUDM/CogVideoX-2b", torch_dtype=torch.float16).to("cuda")
+        >>> pipe = CogVideoXPipeline.from_pretrained("THUDM/CogVideoX-2b", dtype=torch.float16).to("cuda")
         >>> prompt = (
         ...     "A panda, dressed in a small, red jacket and a tiny hat, sits on a wooden stool in a serene bamboo forest. "
         ...     "The panda's fluffy paws strum a miniature acoustic guitar, producing soft, melodic tunes. Nearby, a few other "

src/diffusers/pipelines/cogvideo/pipeline_cogvideox_fun_control.py

@@ -51,7 +51,7 @@
         >>> from diffusers.utils import export_to_video, load_video
 
         >>> pipe = CogVideoXFunControlPipeline.from_pretrained(
-        ...     "alibaba-pai/CogVideoX-Fun-V1.1-5b-Pose", torch_dtype=torch.bfloat16
+        ...     "alibaba-pai/CogVideoX-Fun-V1.1-5b-Pose", dtype=torch.bfloat16
         ... )
         >>> pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
         >>> pipe.to("cuda")

src/diffusers/pipelines/cogvideo/pipeline_cogvideox_image2video.py

@@ -51,7 +51,7 @@
         >>> from diffusers import CogVideoXImageToVideoPipeline
         >>> from diffusers.utils import export_to_video, load_image
 
-        >>> pipe = CogVideoXImageToVideoPipeline.from_pretrained("THUDM/CogVideoX-5b-I2V", torch_dtype=torch.bfloat16)
+        >>> pipe = CogVideoXImageToVideoPipeline.from_pretrained("THUDM/CogVideoX-5b-I2V", dtype=torch.bfloat16)
         >>> pipe.to("cuda")
 
         >>> prompt = "An astronaut hatching from an egg, on the surface of the moon, the darkness and depth of space realised in the background. High quality, ultrarealistic detail and breath-taking movie-like camera shot."

src/diffusers/pipelines/cogvideo/pipeline_cogvideox_video2video.py

@@ -51,7 +51,7 @@
         >>> from diffusers.utils import export_to_video, load_video
 
         >>> # Models: "THUDM/CogVideoX-2b" or "THUDM/CogVideoX-5b"
-        >>> pipe = CogVideoXVideoToVideoPipeline.from_pretrained("THUDM/CogVideoX-5b", torch_dtype=torch.bfloat16)
+        >>> pipe = CogVideoXVideoToVideoPipeline.from_pretrained("THUDM/CogVideoX-5b", dtype=torch.bfloat16)
         >>> pipe.to("cuda")
         >>> pipe.scheduler = CogVideoXDPMScheduler.from_config(pipe.scheduler.config)
 

src/diffusers/pipelines/cogview3/pipeline_cogview3plus.py

@@ -45,7 +45,7 @@
         >>> import torch
         >>> from diffusers import CogView3PlusPipeline
 
-        >>> pipe = CogView3PlusPipeline.from_pretrained("THUDM/CogView3-Plus-3B", torch_dtype=torch.bfloat16)
+        >>> pipe = CogView3PlusPipeline.from_pretrained("THUDM/CogView3-Plus-3B", dtype=torch.bfloat16)
         >>> pipe.to("cuda")
 
         >>> prompt = "A photo of an astronaut riding a horse on mars"

src/diffusers/pipelines/cogview4/pipeline_cogview4.py

@@ -46,7 +46,7 @@
         >>> import torch
         >>> from diffusers import CogView4Pipeline
 
-        >>> pipe = CogView4Pipeline.from_pretrained("THUDM/CogView4-6B", torch_dtype=torch.bfloat16)
+        >>> pipe = CogView4Pipeline.from_pretrained("THUDM/CogView4-6B", dtype=torch.bfloat16)
         >>> pipe.to("cuda")
 
         >>> prompt = "A photo of an astronaut riding a horse on mars"

src/diffusers/pipelines/cogview4/pipeline_cogview4_control.py

@@ -45,7 +45,7 @@
         >>> import torch
         >>> from diffusers import CogView4ControlPipeline
 
-        >>> pipe = CogView4ControlPipeline.from_pretrained("THUDM/CogView4-6B-Control", torch_dtype=torch.bfloat16)
+        >>> pipe = CogView4ControlPipeline.from_pretrained("THUDM/CogView4-6B-Control", dtype=torch.bfloat16)
         >>> control_image = load_image(
         ...     "https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/sd_controlnet/bird_canny.png"
         ... )

src/diffusers/pipelines/consisid/pipeline_consisid.py

@@ -59,7 +59,7 @@
         ...     eva_transform_mean,
         ...     eva_transform_std,
         ... ) = prepare_face_models("BestWishYsh/ConsisID-preview", device="cuda", dtype=torch.bfloat16)
-        >>> pipe = ConsisIDPipeline.from_pretrained("BestWishYsh/ConsisID-preview", torch_dtype=torch.bfloat16)
+        >>> pipe = ConsisIDPipeline.from_pretrained("BestWishYsh/ConsisID-preview", dtype=torch.bfloat16)
         >>> pipe.to("cuda")
 
         >>> # ConsisID works well with long and well-described prompts. Make sure the face in the image is clearly visible (e.g., preferably half-body or full-body).

src/diffusers/pipelines/consistency_models/pipeline_consistency_models.py

@@ -43,7 +43,7 @@
         >>> device = "cuda"
         >>> # Load the cd_imagenet64_l2 checkpoint.
         >>> model_id_or_path = "openai/diffusers-cd_imagenet64_l2"
-        >>> pipe = ConsistencyModelPipeline.from_pretrained(model_id_or_path, torch_dtype=torch.float16)
+        >>> pipe = ConsistencyModelPipeline.from_pretrained(model_id_or_path, dtype=torch.float16)
         >>> pipe.to(device)
 
         >>> # Onestep Sampling

src/diffusers/pipelines/controlnet/pipeline_controlnet.py

@@ -78,9 +78,9 @@
         >>> canny_image = Image.fromarray(image)
 
         >>> # load control net and stable diffusion v1-5
-        >>> controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)
+        >>> controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", dtype=torch.float16)
         >>> pipe = StableDiffusionControlNetPipeline.from_pretrained(
-        ...     "stable-diffusion-v1-5/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16
+        ...     "stable-diffusion-v1-5/stable-diffusion-v1-5", controlnet=controlnet, dtype=torch.float16
         ... )
 
         >>> # speed up diffusion process with faster scheduler and memory optimization

src/diffusers/pipelines/controlnet/pipeline_controlnet_blip_diffusion.py

@@ -45,7 +45,7 @@
         >>> import torch
 
         >>> blip_diffusion_pipe = BlipDiffusionControlNetPipeline.from_pretrained(
-        ...     "Salesforce/blipdiffusion-controlnet", torch_dtype=torch.float16
+        ...     "Salesforce/blipdiffusion-controlnet", dtype=torch.float16
         ... ).to("cuda")
 
         >>> style_subject = "flower"

src/diffusers/pipelines/controlnet/pipeline_controlnet_img2img.py

@@ -77,9 +77,9 @@
         >>> canny_image = Image.fromarray(np_image)
 
         >>> # load control net and stable diffusion v1-5
-        >>> controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)
+        >>> controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", dtype=torch.float16)
         >>> pipe = StableDiffusionControlNetImg2ImgPipeline.from_pretrained(
-        ...     "stable-diffusion-v1-5/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16
+        ...     "stable-diffusion-v1-5/stable-diffusion-v1-5", controlnet=controlnet, dtype=torch.float16
         ... )
 
         >>> # speed up diffusion process with faster scheduler and memory optimization