[Easy] clean up the LCM docstrings.

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

@@ -8,47 +8,8 @@ The abstract of the [paper](https://arxiv.org/pdf/2310.04378.pdf) is as follows:
 
 A demo for the [SimianLuo/LCM_Dreamshaper_v7](https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7) checkpoint can be found [here](https://huggingface.co/spaces/SimianLuo/Latent_Consistency_Model).
 
-This pipeline was contributed by [luosiallen](https://luosiallen.github.io/) and [dg845](https://github.com/dg845).
+The pipelines were contributed by [luosiallen](https://luosiallen.github.io/), [nagolinc](https://github.com/nagolinc), and [dg845](https://github.com/dg845).
 
-## text-to-image
-
-```python
-import torch
-from diffusers import DiffusionPipeline
-
-pipe = DiffusionPipeline.from_pretrained("SimianLuo/LCM_Dreamshaper_v7", torch_dtype=torch.float32)
-
-# To save GPU memory, torch.float16 can be used, but it may compromise image quality.
-pipe.to(torch_device="cuda", torch_dtype=torch.float32)
-
-prompt = "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k"
-
-# Can be set to 1~50 steps. LCM support fast inference even <= 4 steps. Recommend: 1~8 steps.
-num_inference_steps = 4 
-
-images = pipe(prompt=prompt, num_inference_steps=num_inference_steps, guidance_scale=8.0).images
-```
-
-## image-to-image
-
-```python
-import torch
-from diffusers import AutoPipelineForImage2Image
-import PIL
-
-pipe = AutoPipelineForImage2Image.from_pretrained("SimianLuo/LCM_Dreamshaper_v7", torch_dtype=torch.float32)
-
-# To save GPU memory, torch.float16 can be used, but it may compromise image quality.
-pipe.to(torch_device="cuda", torch_dtype=torch.float32)
-
-prompt = "High altitude snowy mountains"
-image = PIL.Image.open("./snowy_mountains.png")
-
-# Can be set to 1~50 steps. LCM support fast inference even <= 4 steps. Recommend: 1~8 steps.
-num_inference_steps = 4 
-
-images = pipe(prompt=prompt, image=image, num_inference_steps=num_inference_steps, guidance_scale=8.0).images
-```
 
 ## LatentConsistencyModelPipeline
 
@@ -62,6 +23,8 @@ images = pipe(prompt=prompt, image=image, num_inference_steps=num_inference_step
     - enable_vae_tiling
     - disable_vae_tiling
 
+## LatentConsistencyModelImg2ImgPipeline
+
 [[autodoc]] LatentConsistencyModelImg2ImgPipeline
     - all
     - __call__

src/diffusers/pipelines/latent_consistency_models/pipeline_latent_consistency_img2img.py

@@ -27,7 +27,14 @@
 from ...models import AutoencoderKL, UNet2DConditionModel
 from ...models.lora import adjust_lora_scale_text_encoder
 from ...schedulers import LCMScheduler
-from ...utils import USE_PEFT_BACKEND, deprecate, logging, scale_lora_layers, unscale_lora_layers
+from ...utils import (
+    USE_PEFT_BACKEND,
+    deprecate,
+    logging,
+    replace_example_docstring,
+    scale_lora_layers,
+    unscale_lora_layers,
+)
 from ...utils.torch_utils import randn_tensor
 from ..pipeline_utils import DiffusionPipeline
 from ..stable_diffusion import StableDiffusionPipelineOutput, StableDiffusionSafetyChecker
@@ -36,6 +43,32 @@
 logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
 
 
+EXAMPLE_DOC_STRING = """
+    Examples:
+        ```py
+        >>> from diffusers import AutoPipelineForImage2Image
+        >>> import torch
+        >>> import PIL
+
+        >>> pipe = DiffusionPipeline.from_pretrained("SimianLuo/LCM_Dreamshaper_v7")
+        >>> # To save GPU memory, torch.float16 can be used, but it may compromise image quality.
+        >>> pipe.to(torch_device="cuda", torch_dtype=torch.float32)
+
+        >>> prompt = "High altitude snowy mountains"
+        >>> image = PIL.Image.open("./snowy_mountains.png")
+
+        >>> # Can be set to 1~50 steps. LCM support fast inference even <= 4 steps. Recommend: 1~8 steps.
+        >>> num_inference_steps = 4
+        >>> images = pipe(
+        ...     prompt=prompt, image=image, num_inference_steps=num_inference_steps, guidance_scale=8.0
+        ... ).images
+
+        >>> images[0].save("image.png")
+        ```
+
+"""
+
+
 class LatentConsistencyModelImg2ImgPipeline(
     DiffusionPipeline, TextualInversionLoaderMixin, LoraLoaderMixin, FromSingleFileMixin
 ):
@@ -486,6 +519,7 @@ def get_timesteps(self, num_inference_steps, strength, device):
         return timesteps, num_inference_steps - t_start
 
     @torch.no_grad()
+    @replace_example_docstring(EXAMPLE_DOC_STRING)
     def __call__(
         self,
         prompt: Union[str, List[str]] = None,
@@ -559,6 +593,8 @@ def __call__(
                 Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
                 the output of the pre-final layer will be used for computing the prompt embeddings.
 
+        Examples:
+
         Returns:
             [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] or `tuple`:
                 If `return_dict` is `True`, [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] is returned,

src/diffusers/pipelines/latent_consistency_models/pipeline_latent_consistency_text2img.py

@@ -26,19 +26,33 @@
 from ...models import AutoencoderKL, UNet2DConditionModel
 from ...models.lora import adjust_lora_scale_text_encoder
 from ...schedulers import LCMScheduler
-from ...utils import (
-    USE_PEFT_BACKEND,
-    logging,
-    scale_lora_layers,
-    unscale_lora_layers,
-)
+from ...utils import USE_PEFT_BACKEND, logging, replace_example_docstring, scale_lora_layers, unscale_lora_layers
 from ...utils.torch_utils import randn_tensor
 from ..pipeline_utils import DiffusionPipeline
 from ..stable_diffusion import StableDiffusionPipelineOutput, StableDiffusionSafetyChecker
 
 
 logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
 
+EXAMPLE_DOC_STRING = """
+    Examples:
+        ```py
+        >>> from diffusers import DiffusionPipeline
+        >>> import torch
+
+        >>> pipe = DiffusionPipeline.from_pretrained("SimianLuo/LCM_Dreamshaper_v7")
+        >>> # To save GPU memory, torch.float16 can be used, but it may compromise image quality.
+        >>> pipe.to(torch_device="cuda", torch_dtype=torch.float32)
+
+        >>> prompt = "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k"
+
+        >>> # Can be set to 1~50 steps. LCM support fast inference even <= 4 steps. Recommend: 1~8 steps.
+        >>> num_inference_steps = 4
+        >>> images = pipe(prompt=prompt, num_inference_steps=num_inference_steps, guidance_scale=8.0).images
+        >>> images[0].save("image.png")
+        ```
+"""
+
 
 class LatentConsistencyModelPipeline(
     DiffusionPipeline, TextualInversionLoaderMixin, LoraLoaderMixin, FromSingleFileMixin
@@ -477,6 +491,7 @@ def check_inputs(
             raise ValueError(f"`prompt` has to be of type `str` or `list` but is {type(prompt)}")
 
     @torch.no_grad()
+    @replace_example_docstring(EXAMPLE_DOC_STRING)
     def __call__(
         self,
         prompt: Union[str, List[str]] = None,
@@ -550,6 +565,8 @@ def __call__(
                 Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
                 the output of the pre-final layer will be used for computing the prompt embeddings.
 
+        Examples:
+
         Returns:
             [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] or `tuple`:
                 If `return_dict` is `True`, [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] is returned,