diffusers 0.23.1__py3-none-any.whl → 0.25.0__py3-none-any.whl

diffusers/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "0.23.1"
+__version__ = "0.25.0"
 
 from typing import TYPE_CHECKING
 
@@ -76,9 +76,11 @@ else:
         [
             "AsymmetricAutoencoderKL",
             "AutoencoderKL",
+            "AutoencoderKLTemporalDecoder",
             "AutoencoderTiny",
             "ConsistencyDecoderVAE",
             "ControlNetModel",
+            "Kandinsky3UNet",
             "ModelMixin",
             "MotionAdapter",
             "MultiAdapter",
@@ -91,9 +93,12 @@ else:
             "UNet2DModel",
             "UNet3DConditionModel",
             "UNetMotionModel",
+            "UNetSpatioTemporalConditionModel",
+            "UVit2DModel",
             "VQModel",
         ]
     )
+
     _import_structure["optimization"] = [
         "get_constant_schedule",
         "get_constant_schedule_with_warmup",
@@ -103,7 +108,6 @@ else:
         "get_polynomial_decay_schedule_with_warmup",
         "get_scheduler",
     ]
-
     _import_structure["pipelines"].extend(
         [
             "AudioPipelineOutput",
@@ -127,6 +131,7 @@ else:
     )
     _import_structure["schedulers"].extend(
         [
+            "AmusedScheduler",
             "CMStochasticIterativeScheduler",
             "DDIMInverseScheduler",
             "DDIMParallelScheduler",
@@ -198,6 +203,9 @@ else:
         [
             "AltDiffusionImg2ImgPipeline",
             "AltDiffusionPipeline",
+            "AmusedImg2ImgPipeline",
+            "AmusedInpaintPipeline",
+            "AmusedPipeline",
             "AnimateDiffPipeline",
             "AudioLDM2Pipeline",
             "AudioLDM2ProjectionModel",
@@ -214,6 +222,8 @@ else:
             "IFPipeline",
             "IFSuperResolutionPipeline",
             "ImageTextPipelineOutput",
+            "Kandinsky3Img2ImgPipeline",
+            "Kandinsky3Pipeline",
             "KandinskyCombinedPipeline",
             "KandinskyImg2ImgCombinedPipeline",
             "KandinskyImg2ImgPipeline",
@@ -274,8 +284,10 @@ else:
             "StableDiffusionXLPipeline",
             "StableUnCLIPImg2ImgPipeline",
             "StableUnCLIPPipeline",
+            "StableVideoDiffusionPipeline",
             "TextToVideoSDPipeline",
             "TextToVideoZeroPipeline",
+            "TextToVideoZeroSDXLPipeline",
             "UnCLIPImageVariationPipeline",
             "UnCLIPPipeline",
             "UniDiffuserModel",
@@ -443,9 +455,11 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
         from .models import (
             AsymmetricAutoencoderKL,
             AutoencoderKL,
+            AutoencoderKLTemporalDecoder,
             AutoencoderTiny,
             ConsistencyDecoderVAE,
             ControlNetModel,
+            Kandinsky3UNet,
             ModelMixin,
             MotionAdapter,
             MultiAdapter,
@@ -458,6 +472,8 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             UNet2DModel,
             UNet3DConditionModel,
             UNetMotionModel,
+            UNetSpatioTemporalConditionModel,
+            UVit2DModel,
             VQModel,
         )
         from .optimization import (
@@ -492,6 +508,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             ScoreSdeVePipeline,
         )
         from .schedulers import (
+            AmusedScheduler,
             CMStochasticIterativeScheduler,
             DDIMInverseScheduler,
             DDIMParallelScheduler,
@@ -546,6 +563,9 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
         from .pipelines import (
             AltDiffusionImg2ImgPipeline,
             AltDiffusionPipeline,
+            AmusedImg2ImgPipeline,
+            AmusedInpaintPipeline,
+            AmusedPipeline,
             AnimateDiffPipeline,
             AudioLDM2Pipeline,
             AudioLDM2ProjectionModel,
@@ -560,6 +580,8 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             IFPipeline,
             IFSuperResolutionPipeline,
             ImageTextPipelineOutput,
+            Kandinsky3Img2ImgPipeline,
+            Kandinsky3Pipeline,
             KandinskyCombinedPipeline,
             KandinskyImg2ImgCombinedPipeline,
             KandinskyImg2ImgPipeline,
@@ -620,8 +642,10 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             StableDiffusionXLPipeline,
             StableUnCLIPImg2ImgPipeline,
             StableUnCLIPPipeline,
+            StableVideoDiffusionPipeline,
             TextToVideoSDPipeline,
             TextToVideoZeroPipeline,
+            TextToVideoZeroSDXLPipeline,
             UnCLIPImageVariationPipeline,
             UnCLIPPipeline,
             UniDiffuserModel,

diffusers/commands/fp16_safetensors.py

@@ -19,6 +19,7 @@ Usage example:
 
 import glob
 import json
+import warnings
 from argparse import ArgumentParser, Namespace
 from importlib import import_module
 
@@ -32,12 +33,12 @@ from . import BaseDiffusersCLICommand
 
 
 def conversion_command_factory(args: Namespace):
-    return FP16SafetensorsCommand(
-        args.ckpt_id,
-        args.fp16,
-        args.use_safetensors,
-        args.use_auth_token,
-    )
+    if args.use_auth_token:
+        warnings.warn(
+            "The `--use_auth_token` flag is deprecated and will be removed in a future version. Authentication is now"
+            " handled automatically if user is logged in."
+        )
+    return FP16SafetensorsCommand(args.ckpt_id, args.fp16, args.use_safetensors)
 
 
 class FP16SafetensorsCommand(BaseDiffusersCLICommand):
@@ -62,7 +63,7 @@ class FP16SafetensorsCommand(BaseDiffusersCLICommand):
         )
         conversion_parser.set_defaults(func=conversion_command_factory)
 
-    def __init__(self, ckpt_id: str, fp16: bool, use_safetensors: bool, use_auth_token: bool):
+    def __init__(self, ckpt_id: str, fp16: bool, use_safetensors: bool):
         self.logger = logging.get_logger("diffusers-cli/fp16_safetensors")
         self.ckpt_id = ckpt_id
         self.local_ckpt_dir = f"/tmp/{ckpt_id}"
@@ -75,8 +76,6 @@ class FP16SafetensorsCommand(BaseDiffusersCLICommand):
                 "When `use_safetensors` and `fp16` both are False, then this command is of no use."
             )
 
-        self.use_auth_token = use_auth_token
-
     def run(self):
         if version.parse(huggingface_hub.__version__) < version.parse("0.9.0"):
             raise ImportError(
@@ -87,7 +86,7 @@ class FP16SafetensorsCommand(BaseDiffusersCLICommand):
             from huggingface_hub import create_commit
             from huggingface_hub._commit_api import CommitOperationAdd
 
-        model_index = hf_hub_download(repo_id=self.ckpt_id, filename="model_index.json", token=self.use_auth_token)
+        model_index = hf_hub_download(repo_id=self.ckpt_id, filename="model_index.json")
         with open(model_index, "r") as f:
             pipeline_class_name = json.load(f)["_class_name"]
         pipeline_class = getattr(import_module("diffusers"), pipeline_class_name)
@@ -96,7 +95,7 @@ class FP16SafetensorsCommand(BaseDiffusersCLICommand):
         # Load the appropriate pipeline. We could have use `DiffusionPipeline`
         # here, but just to avoid any rough edge cases.
         pipeline = pipeline_class.from_pretrained(
-            self.ckpt_id, torch_dtype=torch.float16 if self.fp16 else torch.float32, use_auth_token=self.use_auth_token
+            self.ckpt_id, torch_dtype=torch.float16 if self.fp16 else torch.float32
         )
         pipeline.save_pretrained(
             self.local_ckpt_dir,

diffusers/configuration_utils.py

@@ -27,12 +27,16 @@ from typing import Any, Dict, Tuple, Union
 
 import numpy as np
 from huggingface_hub import create_repo, hf_hub_download
-from huggingface_hub.utils import EntryNotFoundError, RepositoryNotFoundError, RevisionNotFoundError
+from huggingface_hub.utils import (
+    EntryNotFoundError,
+    RepositoryNotFoundError,
+    RevisionNotFoundError,
+    validate_hf_hub_args,
+)
 from requests import HTTPError
 
 from . import __version__
 from .utils import (
-    DIFFUSERS_CACHE,
     HUGGINGFACE_CO_RESOLVE_ENDPOINT,
     DummyObject,
     deprecate,
@@ -95,6 +99,7 @@ class ConfigMixin:
           should only have a `kwargs` argument if at least one argument is deprecated (should be overridden by
           subclass).
     """
+
     config_name = None
     ignore_for_config = []
     has_compatibles = False
@@ -274,6 +279,7 @@ class ConfigMixin:
         return cls.load_config(*args, **kwargs)
 
     @classmethod
+    @validate_hf_hub_args
     def load_config(
         cls,
         pretrained_model_name_or_path: Union[str, os.PathLike],
@@ -310,7 +316,7 @@ class ConfigMixin:
             local_files_only (`bool`, *optional*, defaults to `False`):
                 Whether to only load local model weights and configuration files or not. If set to `True`, the model
                 won't be downloaded from the Hub.
-            use_auth_token (`str` or *bool*, *optional*):
+            token (`str` or *bool*, *optional*):
                 The token to use as HTTP bearer authorization for remote files. If `True`, the token generated from
                 `diffusers-cli login` (stored in `~/.huggingface`) is used.
             revision (`str`, *optional*, defaults to `"main"`):
@@ -328,11 +334,11 @@ class ConfigMixin:
                 A dictionary of all the parameters stored in a JSON configuration file.
 
         """
-        cache_dir = kwargs.pop("cache_dir", DIFFUSERS_CACHE)
+        cache_dir = kwargs.pop("cache_dir", None)
         force_download = kwargs.pop("force_download", False)
         resume_download = kwargs.pop("resume_download", False)
         proxies = kwargs.pop("proxies", None)
-        use_auth_token = kwargs.pop("use_auth_token", None)
+        token = kwargs.pop("token", None)
         local_files_only = kwargs.pop("local_files_only", False)
         revision = kwargs.pop("revision", None)
         _ = kwargs.pop("mirror", None)
@@ -375,7 +381,7 @@ class ConfigMixin:
                     proxies=proxies,
                     resume_download=resume_download,
                     local_files_only=local_files_only,
-                    use_auth_token=use_auth_token,
+                    token=token,
                     user_agent=user_agent,
                     subfolder=subfolder,
                     revision=revision,
@@ -384,8 +390,7 @@ class ConfigMixin:
                 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 `use_auth_token` or log in with `huggingface-cli"
-                    " login`."
+                    " token having permission to this repo with `token` or log in with `huggingface-cli login`."
                 )
             except RevisionNotFoundError:
                 raise EnvironmentError(

diffusers/dependency_versions_check.py

@@ -11,7 +11,6 @@
 # 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 sys
 
 from .dependency_versions_table import deps
 from .utils.versions import require_version, require_version_core

diffusers/dependency_versions_table.py

@@ -1,16 +1,15 @@
 # THIS FILE HAS BEEN AUTOGENERATED. To update:
 # 1. modify the `_deps` dict in setup.py
-# 2. run `make deps_table_update``
+# 2. run `make deps_table_update`
 deps = {
     "Pillow": "Pillow",
     "accelerate": "accelerate>=0.11.0",
     "compel": "compel==0.1.8",
-    "black": "black~=23.1",
     "datasets": "datasets",
     "filelock": "filelock",
     "flax": "flax>=0.4.1",
     "hf-doc-builder": "hf-doc-builder>=0.3.0",
-    "huggingface-hub": "huggingface-hub>=0.13.2",
+    "huggingface-hub": "huggingface-hub>=0.19.4",
     "requests-mock": "requests-mock==1.10.0",
     "importlib_metadata": "importlib_metadata",
     "invisible-watermark": "invisible-watermark>=0.2.0",
@@ -25,15 +24,16 @@ deps = {
     "numpy": "numpy",
     "omegaconf": "omegaconf",
     "parameterized": "parameterized",
-    "peft": "peft<=0.6.2",
+    "peft": "peft>=0.6.0",
     "protobuf": "protobuf>=3.20.3,<4",
     "pytest": "pytest",
     "pytest-timeout": "pytest-timeout",
     "pytest-xdist": "pytest-xdist",
     "python": "python>=3.8.0",
-    "ruff": "ruff==0.0.280",
+    "ruff": "ruff==0.1.5",
     "safetensors": "safetensors>=0.3.1",
     "sentencepiece": "sentencepiece>=0.1.91,!=0.1.92",
+    "GitPython": "GitPython<3.1.19",
     "scipy": "scipy",
     "onnx": "onnx",
     "regex": "regex!=2019.12.17",

diffusers/experimental/rl/value_guided_sampling.py

@@ -113,7 +113,7 @@ class ValueGuidedRLPipeline(DiffusionPipeline):
             prev_x = self.unet(x.permute(0, 2, 1), timesteps).sample.permute(0, 2, 1)
 
             # TODO: verify deprecation of this kwarg
-            x = self.scheduler.step(prev_x, i, x, predict_epsilon=False)["prev_sample"]
+            x = self.scheduler.step(prev_x, i, x)["prev_sample"]
 
             # apply conditions to the trajectory (set the initial state)
             x = self.reset_x0(x, conditions, self.action_dim)