diffusers 0.27.2__py3-none-any.whl → 0.28.1__py3-none-any.whl

diffusers/utils/testing_utils.py

@@ -14,7 +14,6 @@ import time
 import unittest
 import urllib.parse
 from contextlib import contextmanager
-from distutils.util import strtobool
 from io import BytesIO, StringIO
 from pathlib import Path
 from typing import Callable, Dict, List, Optional, Union
@@ -34,6 +33,7 @@ from .import_utils import (
     is_onnx_available,
     is_opencv_available,
     is_peft_available,
+    is_timm_available,
     is_torch_available,
     is_torch_version,
     is_torchsde_available,
@@ -106,10 +106,21 @@ def numpy_cosine_similarity_distance(a, b):
     return distance
 
 
-def print_tensor_test(tensor, filename="test_corrections.txt", expected_tensor_name="expected_slice"):
+def print_tensor_test(
+    tensor,
+    limit_to_slices=None,
+    max_torch_print=None,
+    filename="test_corrections.txt",
+    expected_tensor_name="expected_slice",
+):
+    if max_torch_print:
+        torch.set_printoptions(threshold=10_000)
+
     test_name = os.environ.get("PYTEST_CURRENT_TEST")
     if not torch.is_tensor(tensor):
         tensor = torch.from_numpy(tensor)
+    if limit_to_slices:
+        tensor = tensor[0, -3:, -3:, -1]
 
     tensor_str = str(tensor.detach().cpu().flatten().to(torch.float32)).replace("\n", "")
     # format is usually:
@@ -118,7 +129,7 @@ def print_tensor_test(tensor, filename="test_corrections.txt", expected_tensor_n
     test_file, test_class, test_fn = test_name.split("::")
     test_fn = test_fn.split()[0]
     with open(filename, "a") as f:
-        print(";".join([test_file, test_class, test_fn, output_str]), file=f)
+        print("::".join([test_file, test_class, test_fn, output_str]), file=f)
 
 
 def get_tests_dir(append_path=None):
@@ -142,6 +153,22 @@ def get_tests_dir(append_path=None):
         return tests_dir
 
 
+# Taken from the following PR:
+# https://github.com/huggingface/accelerate/pull/1964
+def str_to_bool(value) -> int:
+    """
+    Converts a string representation of truth to `True` (1) or `False` (0). True values are `y`, `yes`, `t`, `true`,
+    `on`, and `1`; False value are `n`, `no`, `f`, `false`, `off`, and `0`;
+    """
+    value = value.lower()
+    if value in ("y", "yes", "t", "true", "on", "1"):
+        return 1
+    elif value in ("n", "no", "f", "false", "off", "0"):
+        return 0
+    else:
+        raise ValueError(f"invalid truth value {value}")
+
+
 def parse_flag_from_env(key, default=False):
     try:
         value = os.environ[key]
@@ -151,7 +178,7 @@ def parse_flag_from_env(key, default=False):
     else:
         # KEY is set, convert it to True or False.
         try:
-            _value = strtobool(value)
+            _value = str_to_bool(value)
         except ValueError:
             # More values are supported, but let's keep the message simple.
             raise ValueError(f"If set, {key} must be yes or no.")
@@ -229,6 +256,20 @@ def require_torch_accelerator(test_case):
     )
 
 
+def require_torch_multi_gpu(test_case):
+    """
+    Decorator marking a test that requires a multi-GPU setup (in PyTorch). These tests are skipped on a machine without
+    multiple GPUs. To run *only* the multi_gpu tests, assuming all test names contain multi_gpu: $ pytest -sv ./tests
+    -k "multi_gpu"
+    """
+    if not is_torch_available():
+        return unittest.skip("test requires PyTorch")(test_case)
+
+    import torch
+
+    return unittest.skipUnless(torch.cuda.device_count() > 1, "test requires multiple GPUs")(test_case)
+
+
 def require_torch_accelerator_with_fp16(test_case):
     """Decorator marking a test that requires an accelerator with support for the FP16 data type."""
     return unittest.skipUnless(_is_torch_fp16_available(torch_device), "test requires accelerator with fp16 support")(
@@ -300,6 +341,13 @@ def require_peft_backend(test_case):
     return unittest.skipUnless(USE_PEFT_BACKEND, "test requires PEFT backend")(test_case)
 
 
+def require_timm(test_case):
+    """
+    Decorator marking a test that requires timm. These tests are skipped when timm isn't installed.
+    """
+    return unittest.skipUnless(is_timm_available(), "test requires timm")(test_case)
+
+
 def require_peft_version_greater(peft_version):
     """
     Decorator marking a test that requires PEFT backend with a specific version, this would require some specific
@@ -317,6 +365,18 @@ def require_peft_version_greater(peft_version):
     return decorator
 
 
+def require_accelerate_version_greater(accelerate_version):
+    def decorator(test_case):
+        correct_accelerate_version = is_peft_available() and version.parse(
+            version.parse(importlib.metadata.version("accelerate")).base_version
+        ) > version.parse(accelerate_version)
+        return unittest.skipUnless(
+            correct_accelerate_version, f"Test requires accelerate with the version greater than {accelerate_version}."
+        )(test_case)
+
+    return decorator
+
+
 def deprecate_after_peft_backend(test_case):
     """
     Decorator marking a test that will be skipped after PEFT backend
@@ -324,10 +384,15 @@ def deprecate_after_peft_backend(test_case):
     return unittest.skipUnless(not USE_PEFT_BACKEND, "test skipped in favor of PEFT backend")(test_case)
 
 
+def get_python_version():
+    sys_info = sys.version_info
+    major, minor = sys_info.major, sys_info.minor
+    return major, minor
+
+
 def require_python39_or_higher(test_case):
     def python39_available():
-        sys_info = sys.version_info
-        major, minor = sys_info.major, sys_info.minor
+        major, minor = get_python_version()
         return major == 3 and minor >= 9
 
     return unittest.skipUnless(python39_available(), "test requires Python 3.9 or higher")(test_case)

diffusers/utils/torch_utils.py

@@ -14,6 +14,7 @@
 """
 PyTorch utilities: Utilities related to PyTorch
 """
+
 from typing import List, Optional, Tuple, Union
 
 from . import logging

diffusers/video_processor.py

@@ -0,0 +1,113 @@
+# Copyright 2024 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import warnings
+from typing import List, Optional, Union
+
+import numpy as np
+import PIL
+import torch
+
+from .image_processor import VaeImageProcessor, is_valid_image, is_valid_image_imagelist
+
+
+class VideoProcessor(VaeImageProcessor):
+    r"""Simple video processor."""
+
+    def preprocess_video(self, video, height: Optional[int] = None, width: Optional[int] = None) -> torch.Tensor:
+        r"""
+        Preprocesses input video(s).
+
+        Args:
+            video (`List[PIL.Image]`, `List[List[PIL.Image]]`, `torch.Tensor`, `np.array`, `List[torch.Tensor]`, `List[np.array]`):
+                The input video. It can be one of the following:
+                * List of the PIL images.
+                * List of list of PIL images.
+                * 4D Torch tensors (expected shape for each tensor `(num_frames, num_channels, height, width)`).
+                * 4D NumPy arrays (expected shape for each array `(num_frames, height, width, num_channels)`).
+                * List of 4D Torch tensors (expected shape for each tensor `(num_frames, num_channels, height,
+                  width)`).
+                * List of 4D NumPy arrays (expected shape for each array `(num_frames, height, width, num_channels)`).
+                * 5D NumPy arrays: expected shape for each array `(batch_size, num_frames, height, width,
+                  num_channels)`.
+                * 5D Torch tensors: expected shape for each array `(batch_size, num_frames, num_channels, height,
+                  width)`.
+            height (`int`, *optional*, defaults to `None`):
+                The height in preprocessed frames of the video. If `None`, will use the `get_default_height_width()` to
+                get default height.
+            width (`int`, *optional*`, defaults to `None`):
+                The width in preprocessed frames of the video. If `None`, will use get_default_height_width()` to get
+                the default width.
+        """
+        if isinstance(video, list) and isinstance(video[0], np.ndarray) and video[0].ndim == 5:
+            warnings.warn(
+                "Passing `video` as a list of 5d np.ndarray is deprecated."
+                "Please concatenate the list along the batch dimension and pass it as a single 5d np.ndarray",
+                FutureWarning,
+            )
+            video = np.concatenate(video, axis=0)
+        if isinstance(video, list) and isinstance(video[0], torch.Tensor) and video[0].ndim == 5:
+            warnings.warn(
+                "Passing `video` as a list of 5d torch.Tensor is deprecated."
+                "Please concatenate the list along the batch dimension and pass it as a single 5d torch.Tensor",
+                FutureWarning,
+            )
+            video = torch.cat(video, axis=0)
+
+        # ensure the input is a list of videos:
+        # - if it is a batch of videos (5d torch.Tensor or np.ndarray), it is converted to a list of videos (a list of 4d torch.Tensor or np.ndarray)
+        # - if it is is a single video, it is convereted to a list of one video.
+        if isinstance(video, (np.ndarray, torch.Tensor)) and video.ndim == 5:
+            video = list(video)
+        elif isinstance(video, list) and is_valid_image(video[0]) or is_valid_image_imagelist(video):
+            video = [video]
+        elif isinstance(video, list) and is_valid_image_imagelist(video[0]):
+            video = video
+        else:
+            raise ValueError(
+                "Input is in incorrect format. Currently, we only support numpy.ndarray, torch.Tensor, PIL.Image.Image"
+            )
+
+        video = torch.stack([self.preprocess(img, height=height, width=width) for img in video], dim=0)
+
+        # move the number of channels before the number of frames.
+        video = video.permute(0, 2, 1, 3, 4)
+
+        return video
+
+    def postprocess_video(
+        self, video: torch.Tensor, output_type: str = "np"
+    ) -> Union[np.ndarray, torch.Tensor, List[PIL.Image.Image]]:
+        r"""
+        Converts a video tensor to a list of frames for export.
+
+        Args:
+            video (`torch.Tensor`): The video as a tensor.
+            output_type (`str`, defaults to `"np"`): Output type of the postprocessed `video` tensor.
+        """
+        batch_size = video.shape[0]
+        outputs = []
+        for batch_idx in range(batch_size):
+            batch_vid = video[batch_idx].permute(1, 0, 2, 3)
+            batch_output = self.postprocess(batch_vid, output_type)
+            outputs.append(batch_output)
+
+        if output_type == "np":
+            outputs = np.stack(outputs)
+        elif output_type == "pt":
+            outputs = torch.stack(outputs)
+        elif not output_type == "pil":
+            raise ValueError(f"{output_type} does not exist. Please choose one of ['np', 'pt', 'pil']")
+
+        return outputs

{diffusers-0.27.2.dist-info → diffusers-0.28.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: diffusers
-Version: 0.27.2
+Version: 0.28.1
 Summary: State-of-the-art diffusion in PyTorch and JAX.
 Home-page: https://github.com/huggingface/diffusers
 Author: The Hugging Face team (past and future) with the help of all our contributors (https://github.com/huggingface/diffusers/graphs/contributors)
@@ -51,7 +51,7 @@ Requires-Dist: sentencepiece !=0.1.92,>=0.1.91 ; extra == 'dev'
 Requires-Dist: scipy ; extra == 'dev'
 Requires-Dist: torchvision ; extra == 'dev'
 Requires-Dist: transformers >=4.25.1 ; extra == 'dev'
-Requires-Dist: accelerate >=0.11.0 ; extra == 'dev'
+Requires-Dist: accelerate >=0.29.3 ; extra == 'dev'
 Requires-Dist: protobuf <4,>=3.20.3 ; extra == 'dev'
 Requires-Dist: tensorboard ; extra == 'dev'
 Requires-Dist: peft >=0.6.0 ; extra == 'dev'
@@ -90,9 +90,9 @@ Requires-Dist: torchvision ; extra == 'test'
 Requires-Dist: transformers >=4.25.1 ; extra == 'test'
 Provides-Extra: torch
 Requires-Dist: torch >=1.4 ; extra == 'torch'
-Requires-Dist: accelerate >=0.11.0 ; extra == 'torch'
+Requires-Dist: accelerate >=0.29.3 ; extra == 'torch'
 Provides-Extra: training
-Requires-Dist: accelerate >=0.11.0 ; extra == 'training'
+Requires-Dist: accelerate >=0.29.3 ; extra == 'training'
 Requires-Dist: datasets ; extra == 'training'
 Requires-Dist: protobuf <4,>=3.20.3 ; extra == 'training'
 Requires-Dist: tensorboard ; extra == 'training'
@@ -178,7 +178,7 @@ Please refer to the [How to use Stable Diffusion in Apple Silicon](https://huggi
 
 ## Quickstart
 
-Generating outputs is super easy with 🤗 Diffusers. To generate an image from text, use the `from_pretrained` method to load any pretrained diffusion model (browse the [Hub](https://huggingface.co/models?library=diffusers&sort=downloads) for 19000+ checkpoints):
+Generating outputs is super easy with 🤗 Diffusers. To generate an image from text, use the `from_pretrained` method to load any pretrained diffusion model (browse the [Hub](https://huggingface.co/models?library=diffusers&sort=downloads) for 25.000+ checkpoints):
 
 ```python
 from diffusers import DiffusionPipeline
@@ -320,7 +320,7 @@ Also, say 👋 in our public Discord channel <a href="https://discord.gg/G7tWnz9
 - https://github.com/deep-floyd/IF
 - https://github.com/bentoml/BentoML
 - https://github.com/bmaltais/kohya_ss
-- +8000 other amazing GitHub repositories 💪
+- +11.000 other amazing GitHub repositories 💪
 
 Thank you for using us ❤️.
 
@@ -339,7 +339,7 @@ We also want to thank @heejkoo for the very helpful overview of papers, code and
 
 ```bibtex
 @misc{von-platen-etal-2022-diffusers,
-  author = {Patrick von Platen and Suraj Patil and Anton Lozhkov and Pedro Cuenca and Nathan Lambert and Kashif Rasul and Mishig Davaadorj and Thomas Wolf},
+  author = {Patrick von Platen and Suraj Patil and Anton Lozhkov and Pedro Cuenca and Nathan Lambert and Kashif Rasul and Mishig Davaadorj and Dhruv Nair and Sayak Paul and William Berman and Yiyi Xu and Steven Liu and Thomas Wolf},
   title = {Diffusers: State-of-the-art diffusion models},
   year = {2022},
   publisher = {GitHub},