diffusers 0.27.0__py3-none-any.whl → 0.32.2__py3-none-any.whl

diffusers/utils/dynamic_modules_utils.py

@@ -25,21 +25,19 @@ from pathlib import Path
 from typing import Dict, Optional, Union
 from urllib import request
 
-from huggingface_hub import cached_download, hf_hub_download, model_info
-from huggingface_hub.utils import validate_hf_hub_args
+from huggingface_hub import hf_hub_download, model_info
+from huggingface_hub.utils import RevisionNotFoundError, validate_hf_hub_args
 from packaging import version
 
 from .. import __version__
 from . import DIFFUSERS_DYNAMIC_MODULE_NAME, HF_MODULES_CACHE, logging
 
 
-COMMUNITY_PIPELINES_URL = (
-    "https://raw.githubusercontent.com/huggingface/diffusers/{revision}/examples/community/{pipeline}.py"
-)
-
-
 logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
 
+# See https://huggingface.co/datasets/diffusers/community-pipelines-mirror
+COMMUNITY_PIPELINES_MIRROR_ID = "diffusers/community-pipelines-mirror"
+
 
 def get_diffusers_versions():
     url = "https://pypi.org/pypi/diffusers/json"
@@ -201,7 +199,6 @@ def get_cached_module_file(
     module_file: str,
     cache_dir: Optional[Union[str, os.PathLike]] = None,
     force_download: bool = False,
-    resume_download: bool = False,
     proxies: Optional[Dict[str, str]] = None,
     token: Optional[Union[bool, str]] = None,
     revision: Optional[str] = None,
@@ -229,8 +226,6 @@ def get_cached_module_file(
         force_download (`bool`, *optional*, defaults to `False`):
             Whether or not to force to (re-)download the configuration files and override the cached versions if they
             exist.
-        resume_download (`bool`, *optional*, defaults to `False`):
-            Whether or not to delete incompletely received file. Attempts to resume the download if such a file exists.
         proxies (`Dict[str, str]`, *optional*):
             A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128',
             'http://hostname': 'foo.bar:4012'}.` The proxies are used on each request.
@@ -246,8 +241,8 @@ def get_cached_module_file(
 
     <Tip>
 
-    You may pass a token in `token` if you are not logged in (`huggingface-cli login`) and want to use private
-    or [gated models](https://huggingface.co/docs/hub/models-gated#gated-models).
+    You may pass a token in `token` if you are not logged in (`huggingface-cli login`) and want to use private or
+    [gated models](https://huggingface.co/docs/hub/models-gated#gated-models).
 
     </Tip>
 
@@ -281,20 +276,24 @@ def get_cached_module_file(
                 f" {', '.join(available_versions + ['main'])}."
             )
 
-        # community pipeline on GitHub
-        github_url = COMMUNITY_PIPELINES_URL.format(revision=revision, pipeline=pretrained_model_name_or_path)
         try:
-            resolved_module_file = cached_download(
-                github_url,
+            resolved_module_file = hf_hub_download(
+                repo_id=COMMUNITY_PIPELINES_MIRROR_ID,
+                repo_type="dataset",
+                filename=f"{revision}/{pretrained_model_name_or_path}.py",
                 cache_dir=cache_dir,
                 force_download=force_download,
                 proxies=proxies,
-                resume_download=resume_download,
                 local_files_only=local_files_only,
-                token=False,
             )
             submodule = "git"
             module_file = pretrained_model_name_or_path + ".py"
+        except RevisionNotFoundError as e:
+            raise EnvironmentError(
+                f"Revision '{revision}' not found in the community pipelines mirror. Check available revisions on"
+                " https://huggingface.co/datasets/diffusers/community-pipelines-mirror/tree/main."
+                " If you don't find the revision you are looking for, please open an issue on https://github.com/huggingface/diffusers/issues."
+            ) from e
         except EnvironmentError:
             logger.error(f"Could not locate the {module_file} inside {pretrained_model_name_or_path}.")
             raise
@@ -307,7 +306,6 @@ def get_cached_module_file(
                 cache_dir=cache_dir,
                 force_download=force_download,
                 proxies=proxies,
-                resume_download=resume_download,
                 local_files_only=local_files_only,
                 token=token,
             )
@@ -327,10 +325,15 @@ def get_cached_module_file(
         # We always copy local files (we could hash the file to see if there was a change, and give them the name of
         # that hash, to only copy when there is a modification but it seems overkill for now).
         # The only reason we do the copy is to avoid putting too many folders in sys.path.
-        shutil.copy(resolved_module_file, submodule_path / module_file)
+        shutil.copyfile(resolved_module_file, submodule_path / module_file)
         for module_needed in modules_needed:
+            if len(module_needed.split(".")) == 2:
+                module_needed = "/".join(module_needed.split("."))
+                module_folder = module_needed.split("/")[0]
+                if not os.path.exists(submodule_path / module_folder):
+                    os.makedirs(submodule_path / module_folder)
             module_needed = f"{module_needed}.py"
-            shutil.copy(os.path.join(pretrained_model_name_or_path, module_needed), submodule_path / module_needed)
+            shutil.copyfile(os.path.join(pretrained_model_name_or_path, module_needed), submodule_path / module_needed)
     else:
         # Get the commit hash
         # TODO: we will get this info in the etag soon, so retrieve it from there and not here.
@@ -343,16 +346,22 @@ def get_cached_module_file(
         create_dynamic_module(full_submodule)
 
         if not (submodule_path / module_file).exists():
-            shutil.copy(resolved_module_file, submodule_path / module_file)
+            if len(module_file.split("/")) == 2:
+                module_folder = module_file.split("/")[0]
+                if not os.path.exists(submodule_path / module_folder):
+                    os.makedirs(submodule_path / module_folder)
+            shutil.copyfile(resolved_module_file, submodule_path / module_file)
+
         # Make sure we also have every file with relative
         for module_needed in modules_needed:
+            if len(module_needed.split(".")) == 2:
+                module_needed = "/".join(module_needed.split("."))
             if not (submodule_path / module_needed).exists():
                 get_cached_module_file(
                     pretrained_model_name_or_path,
                     f"{module_needed}.py",
                     cache_dir=cache_dir,
                     force_download=force_download,
-                    resume_download=resume_download,
                     proxies=proxies,
                     token=token,
                     revision=revision,
@@ -368,7 +377,6 @@ def get_class_from_dynamic_module(
     class_name: Optional[str] = None,
     cache_dir: Optional[Union[str, os.PathLike]] = None,
     force_download: bool = False,
-    resume_download: bool = False,
     proxies: Optional[Dict[str, str]] = None,
     token: Optional[Union[bool, str]] = None,
     revision: Optional[str] = None,
@@ -405,8 +413,6 @@ def get_class_from_dynamic_module(
         force_download (`bool`, *optional*, defaults to `False`):
             Whether or not to force to (re-)download the configuration files and override the cached versions if they
             exist.
-        resume_download (`bool`, *optional*, defaults to `False`):
-            Whether or not to delete incompletely received file. Attempts to resume the download if such a file exists.
         proxies (`Dict[str, str]`, *optional*):
             A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128',
             'http://hostname': 'foo.bar:4012'}.` The proxies are used on each request.
@@ -422,8 +428,8 @@ def get_class_from_dynamic_module(
 
     <Tip>
 
-    You may pass a token in `token` if you are not logged in (`huggingface-cli login`) and want to use private
-    or [gated models](https://huggingface.co/docs/hub/models-gated#gated-models).
+    You may pass a token in `token` if you are not logged in (`huggingface-cli login`) and want to use private or
+    [gated models](https://huggingface.co/docs/hub/models-gated#gated-models).
 
     </Tip>
 
@@ -443,7 +449,6 @@ def get_class_from_dynamic_module(
         module_file,
         cache_dir=cache_dir,
         force_download=force_download,
-        resume_download=resume_download,
         proxies=proxies,
         token=token,
         revision=revision,

diffusers/utils/export_utils.py

@@ -9,10 +9,7 @@ import numpy as np
 import PIL.Image
 import PIL.ImageOps
 
-from .import_utils import (
-    BACKENDS_MAPPING,
-    is_opencv_available,
-)
+from .import_utils import BACKENDS_MAPPING, is_imageio_available, is_opencv_available
 from .logging import get_logger
 
 
@@ -115,9 +112,9 @@ def export_to_obj(mesh, output_obj_path: str = None):
         f.writelines("\n".join(combined_data))
 
 
-def export_to_video(
+def _legacy_export_to_video(
     video_frames: Union[List[np.ndarray], List[PIL.Image.Image]], output_video_path: str = None, fps: int = 10
-) -> str:
+):
     if is_opencv_available():
         import cv2
     else:
@@ -137,4 +134,51 @@ def export_to_video(
     for i in range(len(video_frames)):
         img = cv2.cvtColor(video_frames[i], cv2.COLOR_RGB2BGR)
         video_writer.write(img)
+
+    return output_video_path
+
+
+def export_to_video(
+    video_frames: Union[List[np.ndarray], List[PIL.Image.Image]], output_video_path: str = None, fps: int = 10
+) -> str:
+    # TODO: Dhruv. Remove by Diffusers release 0.33.0
+    # Added to prevent breaking existing code
+    if not is_imageio_available():
+        logger.warning(
+            (
+                "It is recommended to use `export_to_video` with `imageio` and `imageio-ffmpeg` as a backend. \n"
+                "These libraries are not present in your environment. Attempting to use legacy OpenCV backend to export video. \n"
+                "Support for the OpenCV backend will be deprecated in a future Diffusers version"
+            )
+        )
+        return _legacy_export_to_video(video_frames, output_video_path, fps)
+
+    if is_imageio_available():
+        import imageio
+    else:
+        raise ImportError(BACKENDS_MAPPING["imageio"][1].format("export_to_video"))
+
+    try:
+        imageio.plugins.ffmpeg.get_exe()
+    except AttributeError:
+        raise AttributeError(
+            (
+                "Found an existing imageio backend in your environment. Attempting to export video with imageio. \n"
+                "Unable to find a compatible ffmpeg installation in your environment to use with imageio. Please install via `pip install imageio-ffmpeg"
+            )
+        )
+
+    if output_video_path is None:
+        output_video_path = tempfile.NamedTemporaryFile(suffix=".mp4").name
+
+    if isinstance(video_frames[0], np.ndarray):
+        video_frames = [(frame * 255).astype(np.uint8) for frame in video_frames]
+
+    elif isinstance(video_frames[0], PIL.Image.Image):
+        video_frames = [np.array(frame) for frame in video_frames]
+
+    with imageio.get_writer(output_video_path, fps=fps) as writer:
+        for frame in video_frames:
+            writer.append_data(frame)
+
     return output_video_path

diffusers/utils/hub_utils.py

@@ -14,6 +14,7 @@
 # limitations under the License.
 
 
+import json
 import os
 import re
 import sys
@@ -29,6 +30,8 @@ from huggingface_hub import (
     ModelCardData,
     create_repo,
     hf_hub_download,
+    model_info,
+    snapshot_download,
     upload_folder,
 )
 from huggingface_hub.constants import HF_HUB_CACHE, HF_HUB_DISABLE_TELEMETRY, HF_HUB_OFFLINE
@@ -112,7 +115,8 @@ def load_or_create_model_card(
         repo_id_or_path (`str`):
             The repo id (e.g., "runwayml/stable-diffusion-v1-5") or local path where to look for the model card.
         token (`str`, *optional*):
-            Authentication token. Will default to the stored token. See https://huggingface.co/settings/token for more details.
+            Authentication token. Will default to the stored token. See https://huggingface.co/settings/token for more
+            details.
         is_pipeline (`bool`):
             Boolean to indicate if we're adding tag to a [`DiffusionPipeline`].
         from_training: (`bool`): Boolean flag to denote if the model card is being created from a training script.
@@ -282,7 +286,6 @@ def _get_model_file(
     cache_dir: Optional[str] = None,
     force_download: bool = False,
     proxies: Optional[Dict] = None,
-    resume_download: bool = False,
     local_files_only: bool = False,
     token: Optional[str] = None,
     user_agent: Optional[Union[Dict, str]] = None,
@@ -320,7 +323,6 @@ def _get_model_file(
                     cache_dir=cache_dir,
                     force_download=force_download,
                     proxies=proxies,
-                    resume_download=resume_download,
                     local_files_only=local_files_only,
                     token=token,
                     user_agent=user_agent,
@@ -345,7 +347,6 @@ def _get_model_file(
                 cache_dir=cache_dir,
                 force_download=force_download,
                 proxies=proxies,
-                resume_download=resume_download,
                 local_files_only=local_files_only,
                 token=token,
                 user_agent=user_agent,
@@ -354,44 +355,156 @@ def _get_model_file(
             )
             return model_file
 
-        except RepositoryNotFoundError:
+        except RepositoryNotFoundError as e:
             raise EnvironmentError(
                 f"{pretrained_model_name_or_path} is not a local folder and is not a valid model identifier "
                 "listed on 'https://huggingface.co/models'\nIf this is a private repository, make sure to pass a "
                 "token having permission to this repo with `token` or log in with `huggingface-cli "
                 "login`."
-            )
-        except RevisionNotFoundError:
+            ) from e
+        except RevisionNotFoundError as e:
             raise EnvironmentError(
                 f"{revision} is not a valid git identifier (branch name, tag name or commit id) that exists for "
                 "this model name. Check the model page at "
                 f"'https://huggingface.co/{pretrained_model_name_or_path}' for available revisions."
-            )
-        except EntryNotFoundError:
+            ) from e
+        except EntryNotFoundError as e:
             raise EnvironmentError(
                 f"{pretrained_model_name_or_path} does not appear to have a file named {weights_name}."
-            )
-        except HTTPError as err:
+            ) from e
+        except HTTPError as e:
             raise EnvironmentError(
-                f"There was a specific connection error when trying to load {pretrained_model_name_or_path}:\n{err}"
-            )
-        except ValueError:
+                f"There was a specific connection error when trying to load {pretrained_model_name_or_path}:\n{e}"
+            ) from e
+        except ValueError as e:
             raise EnvironmentError(
                 f"We couldn't connect to '{HUGGINGFACE_CO_RESOLVE_ENDPOINT}' to load this model, couldn't find it"
                 f" in the cached files and it looks like {pretrained_model_name_or_path} is not the path to a"
                 f" directory containing a file named {weights_name} or"
                 " \nCheckout your internet connection or see how to run the library in"
                 " offline mode at 'https://huggingface.co/docs/diffusers/installation#offline-mode'."
-            )
-        except EnvironmentError:
+            ) from e
+        except EnvironmentError as e:
             raise EnvironmentError(
                 f"Can't load the model for '{pretrained_model_name_or_path}'. If you were trying to load it from "
                 "'https://huggingface.co/models', make sure you don't have a local directory with the same name. "
                 f"Otherwise, make sure '{pretrained_model_name_or_path}' is the correct path to a directory "
                 f"containing a file named {weights_name}"
+            ) from e
+
+
+# Adapted from
+# https://github.com/huggingface/transformers/blob/1360801a69c0b169e3efdbb0cd05d9a0e72bfb70/src/transformers/utils/hub.py#L976
+# Differences are in parallelization of shard downloads and checking if shards are present.
+
+
+def _check_if_shards_exist_locally(local_dir, subfolder, original_shard_filenames):
+    shards_path = os.path.join(local_dir, subfolder)
+    shard_filenames = [os.path.join(shards_path, f) for f in original_shard_filenames]
+    for shard_file in shard_filenames:
+        if not os.path.exists(shard_file):
+            raise ValueError(
+                f"{shards_path} does not appear to have a file named {shard_file} which is "
+                "required according to the checkpoint index."
             )
 
 
+def _get_checkpoint_shard_files(
+    pretrained_model_name_or_path,
+    index_filename,
+    cache_dir=None,
+    proxies=None,
+    local_files_only=False,
+    token=None,
+    user_agent=None,
+    revision=None,
+    subfolder="",
+):
+    """
+    For a given model:
+
+    - download and cache all the shards of a sharded checkpoint if `pretrained_model_name_or_path` is a model ID on the
+      Hub
+    - returns the list of paths to all the shards, as well as some metadata.
+
+    For the description of each arg, see [`PreTrainedModel.from_pretrained`]. `index_filename` is the full path to the
+    index (downloaded and cached if `pretrained_model_name_or_path` is a model ID on the Hub).
+    """
+    if not os.path.isfile(index_filename):
+        raise ValueError(f"Can't find a checkpoint index ({index_filename}) in {pretrained_model_name_or_path}.")
+
+    with open(index_filename, "r") as f:
+        index = json.loads(f.read())
+
+    original_shard_filenames = sorted(set(index["weight_map"].values()))
+    sharded_metadata = index["metadata"]
+    sharded_metadata["all_checkpoint_keys"] = list(index["weight_map"].keys())
+    sharded_metadata["weight_map"] = index["weight_map"].copy()
+    shards_path = os.path.join(pretrained_model_name_or_path, subfolder)
+
+    # First, let's deal with local folder.
+    if os.path.isdir(pretrained_model_name_or_path):
+        _check_if_shards_exist_locally(
+            pretrained_model_name_or_path, subfolder=subfolder, original_shard_filenames=original_shard_filenames
+        )
+        return shards_path, sharded_metadata
+
+    # At this stage pretrained_model_name_or_path is a model identifier on the Hub
+    allow_patterns = original_shard_filenames
+    if subfolder is not None:
+        allow_patterns = [os.path.join(subfolder, p) for p in allow_patterns]
+
+    ignore_patterns = ["*.json", "*.md"]
+    # `model_info` call must guarded with the above condition.
+    model_files_info = model_info(pretrained_model_name_or_path, revision=revision, token=token)
+    for shard_file in original_shard_filenames:
+        shard_file_present = any(shard_file in k.rfilename for k in model_files_info.siblings)
+        if not shard_file_present:
+            raise EnvironmentError(
+                f"{shards_path} does not appear to have a file named {shard_file} which is "
+                "required according to the checkpoint index."
+            )
+
+    try:
+        # Load from URL
+        cached_folder = snapshot_download(
+            pretrained_model_name_or_path,
+            cache_dir=cache_dir,
+            proxies=proxies,
+            local_files_only=local_files_only,
+            token=token,
+            revision=revision,
+            allow_patterns=allow_patterns,
+            ignore_patterns=ignore_patterns,
+            user_agent=user_agent,
+        )
+        if subfolder is not None:
+            cached_folder = os.path.join(cached_folder, subfolder)
+
+    # We have already dealt with RepositoryNotFoundError and RevisionNotFoundError when getting the index, so
+    # we don't have to catch them here. We have also dealt with EntryNotFoundError.
+    except HTTPError as e:
+        raise EnvironmentError(
+            f"We couldn't connect to '{HUGGINGFACE_CO_RESOLVE_ENDPOINT}' to load {pretrained_model_name_or_path}. You should try"
+            " again after checking your internet connection."
+        ) from e
+
+    return cached_folder, sharded_metadata
+
+
+def _check_legacy_sharding_variant_format(folder: str = None, filenames: List[str] = None, variant: str = None):
+    if filenames and folder:
+        raise ValueError("Both `filenames` and `folder` cannot be provided.")
+    if not filenames:
+        filenames = []
+        for _, _, files in os.walk(folder):
+            for file in files:
+                filenames.append(os.path.basename(file))
+    transformers_index_format = r"\d{5}-of-\d{5}"
+    variant_file_re = re.compile(rf".*-{transformers_index_format}\.{variant}\.[a-z]+$")
+    return any(variant_file_re.match(f) is not None for f in filenames)
+
+
 class PushToHubMixin:
     """
     A Mixin to push a model, scheduler, or pipeline to the Hugging Face Hub.
@@ -442,7 +555,8 @@ class PushToHubMixin:
             commit_message (`str`, *optional*):
                 Message to commit while pushing. Default to `"Upload {object}"`.
             private (`bool`, *optional*):
-                Whether or not the repository created should be private.
+                Whether to make the repo private. If `None` (default), the repo will be public unless the
+                organization's default is private. This value is ignored if the repo already exists.
             token (`str`, *optional*):
                 The token to use as HTTP bearer authorization for remote files. The token generated when running
                 `huggingface-cli login` (stored in `~/.huggingface`).