[docs] Migrate syntax (#12390)

* change syntax

* make style

src/diffusers/pipelines/pipeline_flax_utils.py

@@ -276,12 +276,8 @@ class FlaxDiffusionPipeline(ConfigMixin, PushToHubMixin):
                 Can be used to overwrite load and saveable variables (the pipeline components) of the specific pipeline
                 class. The overwritten components are passed directly to the pipelines `__init__` method.
 
-        <Tip>
-
-        To use private or [gated models](https://huggingface.co/docs/hub/models-gated#gated-models), log-in with `hf
-        auth login`.
-
-        </Tip>
+        > [!TIP] > To use private or [gated models](https://huggingface.co/docs/hub/models-gated#gated-models), log-in
+        with `hf > auth login`.
 
         Examples:
 

src/diffusers/pipelines/pipeline_utils.py

@@ -372,12 +372,8 @@ class DiffusionPipeline(ConfigMixin, PushToHubMixin):
         Performs Pipeline dtype and/or device conversion. A torch.dtype and torch.device are inferred from the
         arguments of `self.to(*args, **kwargs).`
 
-        <Tip>
-
-            If the pipeline already has the correct torch.dtype and torch.device, then it is returned as is. Otherwise,
-            the returned pipeline is a copy of self with the desired torch.dtype and torch.device.
-
-        </Tip>
+        > [!TIP] > If the pipeline already has the correct torch.dtype and torch.device, then it is returned as is.
+        Otherwise, > the returned pipeline is a copy of self with the desired torch.dtype and torch.device.
 
 
         Here are the ways to call `to`:
@@ -627,11 +623,7 @@ class DiffusionPipeline(ConfigMixin, PushToHubMixin):
                 `torch.float32` is used.
             custom_pipeline (`str`, *optional*):
 
-                <Tip warning={true}>
-
-                🧪 This is an experimental feature and may change in the future.
-
-                </Tip>
+                > [!WARNING] > 🧪 This is an experimental feature and may change in the future.
 
                 Can be either:
 
@@ -716,12 +708,8 @@ class DiffusionPipeline(ConfigMixin, PushToHubMixin):
             dduf_file(`str`, *optional*):
                 Load weights from the specified dduf file.
 
-        <Tip>
-
-        To use private or [gated](https://huggingface.co/docs/hub/models-gated#gated-models) models, log-in with `hf
-        auth login`.
-
-        </Tip>
+        > [!TIP] > To use private or [gated](https://huggingface.co/docs/hub/models-gated#gated-models) models, log-in
+        with `hf > auth login`.
 
         Examples:
 
@@ -1508,11 +1496,7 @@ class DiffusionPipeline(ConfigMixin, PushToHubMixin):
                     - A path to a *directory* (`./my_pipeline_directory/`) containing a custom pipeline. The directory
                       must contain a file called `pipeline.py` that defines the custom pipeline.
 
-                <Tip warning={true}>
-
-                🧪 This is an experimental feature and may change in the future.
-
-                </Tip>
+                > [!WARNING] > 🧪 This is an experimental feature and may change in the future.
 
                 For more information on how to load and create custom pipelines, take a look at [How to contribute a
                 community pipeline](https://huggingface.co/docs/diffusers/main/en/using-diffusers/contribute_pipeline).
@@ -1566,12 +1550,8 @@ class DiffusionPipeline(ConfigMixin, PushToHubMixin):
             `os.PathLike`:
                 A path to the downloaded pipeline.
 
-        <Tip>
-
-        To use private or [gated models](https://huggingface.co/docs/hub/models-gated#gated-models), log-in with `hf
-        auth login
-
-        </Tip>
+        > [!TIP] > To use private or [gated models](https://huggingface.co/docs/hub/models-gated#gated-models), log-in
+        with `hf > auth login
 
         """
         cache_dir = kwargs.pop("cache_dir", None)
@@ -1944,12 +1924,8 @@ class DiffusionPipeline(ConfigMixin, PushToHubMixin):
         option is enabled, you should observe lower GPU memory usage and a potential speed up during inference. Speed
         up during training is not guaranteed.
 
-        <Tip warning={true}>
-
-        ⚠️ When memory efficient attention and sliced attention are both enabled, memory efficient attention takes
-        precedent.
-
-        </Tip>
+        > [!WARNING] > ⚠️ When memory efficient attention and sliced attention are both enabled, memory efficient
+        attention takes > precedent.
 
         Parameters:
             attention_op (`Callable`, *optional*):
@@ -2005,13 +1981,10 @@ class DiffusionPipeline(ConfigMixin, PushToHubMixin):
         in slices to compute attention in several steps. For more than one attention head, the computation is performed
         sequentially over each head. This is useful to save some memory in exchange for a small speed decrease.
 
-        <Tip warning={true}>
-
-        ⚠️ Don't enable attention slicing if you're already using `scaled_dot_product_attention` (SDPA) from PyTorch
-        2.0 or xFormers. These attention computations are already very memory efficient so you won't need to enable
-        this function. If you enable attention slicing with SDPA or xFormers, it can lead to serious slow downs!
-
-        </Tip>
+        > [!WARNING] > ⚠️ Don't enable attention slicing if you're already using `scaled_dot_product_attention` (SDPA)
+        from PyTorch > 2.0 or xFormers. These attention computations are already very memory efficient so you won't
+        need to enable > this function. If you enable attention slicing with SDPA or xFormers, it can lead to serious
+        slow downs!
 
         Args:
             slice_size (`str` or `int`, *optional*, defaults to `"auto"`):
@@ -2288,11 +2261,7 @@ class StableDiffusionMixin:
         Enables fused QKV projections. For self-attention modules, all projection matrices (i.e., query, key, value)
         are fused. For cross-attention modules, key and value projection matrices are fused.
 
-        <Tip warning={true}>
-
-        This API is 🧪 experimental.
-
-        </Tip>
+        > [!WARNING] > This API is 🧪 experimental.
 
         Args:
             unet (`bool`, defaults to `True`): To apply fusion on the UNet.
@@ -2317,11 +2286,7 @@ class StableDiffusionMixin:
     def unfuse_qkv_projections(self, unet: bool = True, vae: bool = True):
         """Disable QKV projection fusion if enabled.
 
-        <Tip warning={true}>
-
-        This API is 🧪 experimental.
-
-        </Tip>
+        > [!WARNING] > This API is 🧪 experimental.
 
         Args:
             unet (`bool`, defaults to `True`): To apply fusion on the UNet.

src/diffusers/pipelines/stable_diffusion/pipeline_flax_stable_diffusion.py

@@ -349,12 +349,8 @@ class FlaxStableDiffusionPipeline(FlaxDiffusionPipeline):
             jit (`bool`, defaults to `False`):
                 Whether to run `pmap` versions of the generation and safety scoring functions.
 
-                    <Tip warning={true}>
-
-                    This argument exists because `__call__` is not yet end-to-end pmap-able. It will be removed in a
-                    future release.
-
-                    </Tip>
+                    > [!WARNING] > This argument exists because `__call__` is not yet end-to-end pmap-able. It will be
+                    removed in a > future release.
 
             return_dict (`bool`, *optional*, defaults to `True`):
                 Whether or not to return a [`~pipelines.stable_diffusion.FlaxStableDiffusionPipelineOutput`] instead of

src/diffusers/pipelines/stable_diffusion/pipeline_flax_stable_diffusion_img2img.py

@@ -389,12 +389,8 @@ class FlaxStableDiffusionImg2ImgPipeline(FlaxDiffusionPipeline):
             jit (`bool`, defaults to `False`):
                 Whether to run `pmap` versions of the generation and safety scoring functions.
 
-                    <Tip warning={true}>
-
-                    This argument exists because `__call__` is not yet end-to-end pmap-able. It will be removed in a
-                    future release.
-
-                    </Tip>
+                    > [!WARNING] > This argument exists because `__call__` is not yet end-to-end pmap-able. It will be
+                    removed in a > future release.
 
         Examples:
 

src/diffusers/pipelines/stable_diffusion/pipeline_flax_stable_diffusion_inpaint.py

@@ -103,11 +103,7 @@ class FlaxStableDiffusionInpaintPipeline(FlaxDiffusionPipeline):
     r"""
     Flax-based pipeline for text-guided image inpainting using Stable Diffusion.
 
-    <Tip warning={true}>
-
-    🧪 This is an experimental feature!
-
-    </Tip>
+    > [!WARNING] > 🧪 This is an experimental feature!
 
     This model inherits from [`FlaxDiffusionPipeline`]. Check the superclass documentation for the generic methods
     implemented for all pipelines (downloading, saving, running on a particular device, etc.).
@@ -435,12 +431,8 @@ class FlaxStableDiffusionInpaintPipeline(FlaxDiffusionPipeline):
             jit (`bool`, defaults to `False`):
                 Whether to run `pmap` versions of the generation and safety scoring functions.
 
-                    <Tip warning={true}>
-
-                    This argument exists because `__call__` is not yet end-to-end pmap-able. It will be removed in a
-                    future release.
-
-                    </Tip>
+                    > [!WARNING] > This argument exists because `__call__` is not yet end-to-end pmap-able. It will be
+                    removed in a > future release.
 
             return_dict (`bool`, *optional*, defaults to `True`):
                 Whether or not to return a [`~pipelines.stable_diffusion.FlaxStableDiffusionPipelineOutput`] instead of

src/diffusers/pipelines/stable_diffusion_diffedit/pipeline_stable_diffusion_diffedit.py

@@ -249,11 +249,7 @@ class StableDiffusionDiffEditPipeline(
     StableDiffusionLoraLoaderMixin,
 ):
     r"""
-    <Tip warning={true}>
-
-    This is an experimental feature!
-
-    </Tip>
+    > [!WARNING] > This is an experimental feature!
 
     Pipeline for text-guided image inpainting using Stable Diffusion and DiffEdit.
 

src/diffusers/pipelines/stable_diffusion_k_diffusion/pipeline_stable_diffusion_k_diffusion.py

@@ -81,11 +81,7 @@ class StableDiffusionKDiffusionPipeline(
         - [`~loaders.StableDiffusionLoraLoaderMixin.load_lora_weights`] for loading LoRA weights
         - [`~loaders.StableDiffusionLoraLoaderMixin.save_lora_weights`] for saving LoRA weights
 
-    <Tip warning={true}>
-
-        This is an experimental pipeline and is likely to change in the future.
-
-    </Tip>
+    > [!WARNING] > This is an experimental pipeline and is likely to change in the future.
 
     Args:
         vae ([`AutoencoderKL`]):

src/diffusers/schedulers/deprecated/scheduling_karras_ve.py

@@ -53,13 +53,9 @@ class KarrasVeScheduler(SchedulerMixin, ConfigMixin):
     This model inherits from [`SchedulerMixin`] and [`ConfigMixin`]. Check the superclass documentation for the generic
     methods the library implements for all schedulers such as loading and saving.
 
-    <Tip>
-
-    For more details on the parameters, see [Appendix E](https://huggingface.co/papers/2206.00364). The grid search
-    values used to find the optimal `{s_noise, s_churn, s_min, s_max}` for a specific model are described in Table 5 of
-    the paper.
-
-    </Tip>
+    > [!TIP] > For more details on the parameters, see [Appendix E](https://huggingface.co/papers/2206.00364). The grid
+    search > values used to find the optimal `{s_noise, s_churn, s_min, s_max}` for a specific model are described in
+    Table 5 of > the paper.
 
     Args:
         sigma_min (`float`, defaults to 0.02):

src/diffusers/schedulers/scheduling_consistency_models.py

@@ -268,11 +268,7 @@ class CMStochasticIterativeScheduler(SchedulerMixin, ConfigMixin):
         Gets the scalings used in the consistency model parameterization (from Appendix C of the
         [paper](https://huggingface.co/papers/2303.01469)) to enforce boundary condition.
 
-        <Tip>
-
-        `epsilon` in the equations for `c_skip` and `c_out` is set to `sigma_min`.
-
-        </Tip>
+        > [!TIP] > `epsilon` in the equations for `c_skip` and `c_out` is set to `sigma_min`.
 
         Args:
             sigma (`torch.Tensor`):

src/diffusers/schedulers/scheduling_cosine_dpmsolver_multistep.py

@@ -304,12 +304,8 @@ class CosineDPMSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
         designed to discretize an integral of the noise prediction model, and DPM-Solver++ is designed to discretize an
         integral of the data prediction model.
 
-        <Tip>
-
-        The algorithm and model type are decoupled. You can use either DPMSolver or DPMSolver++ for both noise
-        prediction and data prediction models.
-
-        </Tip>
+        > [!TIP] > The algorithm and model type are decoupled. You can use either DPMSolver or DPMSolver++ for both
+        noise > prediction and data prediction models.
 
         Args:
             model_output (`torch.Tensor`):

src/diffusers/schedulers/scheduling_dpmsolver_multistep.py

@@ -630,12 +630,8 @@ class DPMSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
         designed to discretize an integral of the noise prediction model, and DPM-Solver++ is designed to discretize an
         integral of the data prediction model.
 
-        <Tip>
-
-        The algorithm and model type are decoupled. You can use either DPMSolver or DPMSolver++ for both noise
-        prediction and data prediction models.
-
-        </Tip>
+        > [!TIP] > The algorithm and model type are decoupled. You can use either DPMSolver or DPMSolver++ for both
+        noise > prediction and data prediction models.
 
         Args:
             model_output (`torch.Tensor`):

src/diffusers/schedulers/scheduling_dpmsolver_multistep_inverse.py

@@ -491,12 +491,8 @@ class DPMSolverMultistepInverseScheduler(SchedulerMixin, ConfigMixin):
         designed to discretize an integral of the noise prediction model, and DPM-Solver++ is designed to discretize an
         integral of the data prediction model.
 
-        <Tip>
-
-        The algorithm and model type are decoupled. You can use either DPMSolver or DPMSolver++ for both noise
-        prediction and data prediction models.
-
-        </Tip>
+        > [!TIP] > The algorithm and model type are decoupled. You can use either DPMSolver or DPMSolver++ for both
+        noise > prediction and data prediction models.
 
         Args:
             model_output (`torch.Tensor`):

src/diffusers/schedulers/scheduling_dpmsolver_singlestep.py

@@ -568,12 +568,8 @@ class DPMSolverSinglestepScheduler(SchedulerMixin, ConfigMixin):
         designed to discretize an integral of the noise prediction model, and DPM-Solver++ is designed to discretize an
         integral of the data prediction model.
 
-        <Tip>
-
-        The algorithm and model type are decoupled. You can use either DPMSolver or DPMSolver++ for both noise
-        prediction and data prediction models.
-
-        </Tip>
+        > [!TIP] > The algorithm and model type are decoupled. You can use either DPMSolver or DPMSolver++ for both
+        noise > prediction and data prediction models.
 
         Args:
             model_output (`torch.Tensor`):

src/diffusers/schedulers/scheduling_edm_dpmsolver_multistep.py

@@ -370,12 +370,8 @@ class EDMDPMSolverMultistepScheduler(SchedulerMixin, ConfigMixin):
         designed to discretize an integral of the noise prediction model, and DPM-Solver++ is designed to discretize an
         integral of the data prediction model.
 
-        <Tip>
-
-        The algorithm and model type are decoupled. You can use either DPMSolver or DPMSolver++ for both noise
-        prediction and data prediction models.
-
-        </Tip>
+        > [!TIP] > The algorithm and model type are decoupled. You can use either DPMSolver or DPMSolver++ for both
+        noise > prediction and data prediction models.
 
         Args:
             model_output (`torch.Tensor`):

src/diffusers/schedulers/scheduling_sasolver.py

@@ -500,12 +500,8 @@ class SASolverScheduler(SchedulerMixin, ConfigMixin):
         Noise_prediction is designed to discretize an integral of the noise prediction model, and data_prediction is
         designed to discretize an integral of the data prediction model.
 
-        <Tip>
-
-        The algorithm and model type are decoupled. You can use either data_prediction or noise_prediction for both
-        noise prediction and data prediction models.
-
-        </Tip>
+        > [!TIP] > The algorithm and model type are decoupled. You can use either data_prediction or noise_prediction
+        for both > noise prediction and data prediction models.
 
         Args:
             model_output (`torch.Tensor`):

src/diffusers/schedulers/scheduling_utils.py

@@ -138,15 +138,11 @@ class SchedulerMixin(PushToHubMixin):
                 The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier
                 allowed by Git.
 
-        <Tip>
-
-        To use private or [gated models](https://huggingface.co/docs/hub/models-gated#gated-models), log-in with `hf
-        auth login`. You can also activate the special
-        ["offline-mode"](https://huggingface.co/diffusers/installation.html#offline-mode) to use this method in a
+        > [!TIP] > To use private or [gated models](https://huggingface.co/docs/hub/models-gated#gated-models), log-in
+        with `hf > auth login`. You can also activate the special >
+        ["offline-mode"](https://huggingface.co/diffusers/installation.html#offline-mode) to use this method in a >
         firewalled environment.
 
-        </Tip>
-
         """
         config, kwargs, commit_hash = cls.load_config(
             pretrained_model_name_or_path=pretrained_model_name_or_path,

src/diffusers/schedulers/scheduling_utils_flax.py

@@ -120,19 +120,12 @@ class FlaxSchedulerMixin(PushToHubMixin):
                 git-based system for storing models and other artifacts on huggingface.co, so `revision` can be any
                 identifier allowed by git.
 
-        <Tip>
+        > [!TIP] > It is required to be logged in (`hf auth login`) when you want to use private or [gated >
+        models](https://huggingface.co/docs/hub/models-gated#gated-models).
 
-         It is required to be logged in (`hf auth login`) when you want to use private or [gated
-         models](https://huggingface.co/docs/hub/models-gated#gated-models).
-
-        </Tip>
-
-        <Tip>
-
-        Activate the special ["offline-mode"](https://huggingface.co/transformers/installation.html#offline-mode) to
-        use this method in a firewalled environment.
-
-        </Tip>
+        > [!TIP] > Activate the special
+        ["offline-mode"](https://huggingface.co/transformers/installation.html#offline-mode) to > use this method in a
+        firewalled environment.
 
         """
         logger.warning(

src/diffusers/utils/dynamic_modules_utils.py

@@ -290,12 +290,8 @@ def get_cached_module_file(
         local_files_only (`bool`, *optional*, defaults to `False`):
             If `True`, will only try to load the tokenizer configuration from local files.
 
-    <Tip>
-
-    You may pass a token in `token` if you are not logged in (`hf auth login`) and want to use private or [gated
-    models](https://huggingface.co/docs/hub/models-gated#gated-models).
-
-    </Tip>
+    > [!TIP] > You may pass a token in `token` if you are not logged in (`hf auth login`) and want to use private or
+    [gated > models](https://huggingface.co/docs/hub/models-gated#gated-models).
 
     Returns:
         `str`: The path to the module inside the cache.
@@ -440,12 +436,8 @@ def get_class_from_dynamic_module(
     """
     Extracts a class from a module file, present in the local folder or repository of a model.
 
-    <Tip warning={true}>
-
-    Calling this function will execute the code in the module file found locally or downloaded from the Hub. It should
-    therefore only be called on trusted repos.
-
-    </Tip>
+    > [!WARNING] > Calling this function will execute the code in the module file found locally or downloaded from the
+    Hub. It should > therefore only be called on trusted repos.
 
     Args:
         pretrained_model_name_or_path (`str` or `os.PathLike`):
@@ -480,12 +472,8 @@ def get_class_from_dynamic_module(
         local_files_only (`bool`, *optional*, defaults to `False`):
             If `True`, will only try to load the tokenizer configuration from local files.
 
-    <Tip>
-
-    You may pass a token in `token` if you are not logged in (`hf auth login`) and want to use private or [gated
-    models](https://huggingface.co/docs/hub/models-gated#gated-models).
-
-    </Tip>
+    > [!TIP] > You may pass a token in `token` if you are not logged in (`hf auth login`) and want to use private or
+    [gated > models](https://huggingface.co/docs/hub/models-gated#gated-models).
 
     Returns:
         `type`: The class, dynamically imported from the module.

src/diffusers/utils/outputs.py

@@ -43,12 +43,8 @@ class BaseOutput(OrderedDict):
     tuple) or strings (like a dictionary) that will ignore the `None` attributes. Otherwise behaves like a regular
     Python dictionary.
 
-    <Tip warning={true}>
-
-    You can't unpack a [`BaseOutput`] directly. Use the [`~utils.BaseOutput.to_tuple`] method to convert it to a tuple
-    first.
-
-    </Tip>
+    > [!WARNING] > You can't unpack a [`BaseOutput`] directly. Use the [`~utils.BaseOutput.to_tuple`] method to convert
+    it to a tuple > first.
     """
 
     def __init_subclass__(cls) -> None: