[Bot] Update inference types (#2791)

* Update inference types (automated commit)

* widget

* tmp revert generate_kwargs

* code quality

---------

Co-authored-by: Wauplin <[email protected]>
Co-authored-by: Lucain Pouget <[email protected]>

docs/source/en/package_reference/inference_types.md

@@ -309,8 +309,6 @@ This part of the lib is still under development and will be improved in future r
 
 [[autodoc]] huggingface_hub.TextToImageParameters
 
-[[autodoc]] huggingface_hub.TextToImageTargetSize
-
 
 
 ## text_to_speech

docs/source/ko/package_reference/inference_types.md

@@ -308,8 +308,6 @@ rendered properly in your Markdown viewer.
 
 [[autodoc]] huggingface_hub.TextToImageParameters
 
-[[autodoc]] huggingface_hub.TextToImageTargetSize
-
 
 
 ## text_to_speech[[huggingface_hub.TextToSpeechGenerationParameters]]

src/huggingface_hub/__init__.py

@@ -392,7 +392,6 @@
         "TextToImageInput",
         "TextToImageOutput",
         "TextToImageParameters",
-        "TextToImageTargetSize",
         "TextToSpeechEarlyStoppingEnum",
         "TextToSpeechGenerationParameters",
         "TextToSpeechInput",
@@ -702,7 +701,6 @@
     "TextToImageInput",
     "TextToImageOutput",
     "TextToImageParameters",
-    "TextToImageTargetSize",
     "TextToSpeechEarlyStoppingEnum",
     "TextToSpeechGenerationParameters",
     "TextToSpeechInput",
@@ -1334,7 +1332,6 @@ def __dir__():
         TextToImageInput,  # noqa: F401
         TextToImageOutput,  # noqa: F401
         TextToImageParameters,  # noqa: F401
-        TextToImageTargetSize,  # noqa: F401
         TextToSpeechEarlyStoppingEnum,  # noqa: F401
         TextToSpeechGenerationParameters,  # noqa: F401
         TextToSpeechInput,  # noqa: F401

src/huggingface_hub/inference/_client.py

@@ -2395,8 +2395,8 @@ def text_to_image(
         prompt: str,
         *,
         negative_prompt: Optional[str] = None,
-        height: Optional[float] = None,
-        width: Optional[float] = None,
+        height: Optional[int] = None,
+        width: Optional[int] = None,
         num_inference_steps: Optional[int] = None,
         guidance_scale: Optional[float] = None,
         model: Optional[str] = None,
@@ -2422,10 +2422,10 @@ def text_to_image(
                 The prompt to generate an image from.
             negative_prompt (`str`, *optional*):
                 One prompt to guide what NOT to include in image generation.
-            height (`float`, *optional*):
-                The height in pixels of the image to generate.
-            width (`float`, *optional*):
-                The width in pixels of the image to generate.
+            height (`int`, *optional*):
+                The height in pixels of the output image
+            width (`int`, *optional*):
+                The width in pixels of the output image
             num_inference_steps (`int`, *optional*):
                 The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                 expense of slower inference.

src/huggingface_hub/inference/_generated/_async_client.py

@@ -2451,8 +2451,8 @@ async def text_to_image(
         prompt: str,
         *,
         negative_prompt: Optional[str] = None,
-        height: Optional[float] = None,
-        width: Optional[float] = None,
+        height: Optional[int] = None,
+        width: Optional[int] = None,
         num_inference_steps: Optional[int] = None,
         guidance_scale: Optional[float] = None,
         model: Optional[str] = None,
@@ -2478,10 +2478,10 @@ async def text_to_image(
                 The prompt to generate an image from.
             negative_prompt (`str`, *optional*):
                 One prompt to guide what NOT to include in image generation.
-            height (`float`, *optional*):
-                The height in pixels of the image to generate.
-            width (`float`, *optional*):
-                The width in pixels of the image to generate.
+            height (`int`, *optional*):
+                The height in pixels of the output image
+            width (`int`, *optional*):
+                The width in pixels of the output image
             num_inference_steps (`int`, *optional*):
                 The number of denoising steps. More denoising steps usually lead to a higher quality image at the
                 expense of slower inference.

src/huggingface_hub/inference/_generated/types/__init__.py

@@ -141,7 +141,7 @@
     TextToAudioOutput,
     TextToAudioParameters,
 )
-from .text_to_image import TextToImageInput, TextToImageOutput, TextToImageParameters, TextToImageTargetSize
+from .text_to_image import TextToImageInput, TextToImageOutput, TextToImageParameters
 from .text_to_speech import (
     TextToSpeechEarlyStoppingEnum,
     TextToSpeechGenerationParameters,

src/huggingface_hub/inference/_generated/types/feature_extraction.py

@@ -4,7 +4,7 @@
 #   - script: https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-codegen.ts
 #   - specs:  https://github.com/huggingface/huggingface.js/tree/main/packages/tasks/src/tasks.
 from dataclasses import dataclass
-from typing import Literal, Optional
+from typing import List, Literal, Optional, Union
 
 from .base import BaseInferenceType
 
@@ -20,8 +20,8 @@ class FeatureExtractionInput(BaseInferenceType):
     https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/scripts/inference-tei-import.ts.
     """
 
-    inputs: str
-    """The text to embed."""
+    inputs: Union[List[str], str]
+    """The text or list of texts to embed."""
     normalize: Optional[bool] = None
     prompt_name: Optional[str] = None
     """The name of the prompt that should be used by for encoding. If not set, no prompt

src/huggingface_hub/inference/_generated/types/text_to_image.py

@@ -9,14 +9,6 @@
 from .base import BaseInferenceType
 
 
-@dataclass
-class TextToImageTargetSize(BaseInferenceType):
-    """The size in pixel of the output image"""
-
-    height: int
-    width: int
-
-
 @dataclass
 class TextToImageParameters(BaseInferenceType):
     """Additional inference parameters for Text To Image"""
@@ -25,6 +17,8 @@ class TextToImageParameters(BaseInferenceType):
     """A higher guidance scale value encourages the model to generate images closely linked to
     the text prompt, but values too high may cause saturation and other artifacts.
     """
+    height: Optional[int] = None
+    """The height in pixels of the output image"""
     negative_prompt: Optional[str] = None
     """One prompt to guide what NOT to include in image generation."""
     num_inference_steps: Optional[int] = None
@@ -35,6 +29,8 @@ class TextToImageParameters(BaseInferenceType):
     """Override the scheduler with a compatible one."""
     seed: Optional[int] = None
     """Seed for the random number generator."""
+    width: Optional[int] = None
+    """The width in pixels of the output image"""
 
 
 @dataclass