diffusers 0.30.2__tar.gz → 0.31.0__tar.gz

{diffusers-0.30.2/src/diffusers.egg-info → diffusers-0.31.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: diffusers
-Version: 0.30.2
+Version: 0.31.0
 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)
@@ -62,7 +62,7 @@ Requires-Dist: scipy; extra == "test"
 Requires-Dist: torchvision; extra == "test"
 Requires-Dist: transformers>=4.41.2; extra == "test"
 Provides-Extra: torch
-Requires-Dist: torch>=1.4; extra == "torch"
+Requires-Dist: torch<2.5.0,>=1.4; extra == "torch"
 Requires-Dist: accelerate>=0.31.0; extra == "torch"
 Provides-Extra: flax
 Requires-Dist: jax>=0.4.1; extra == "flax"
@@ -97,7 +97,7 @@ Requires-Dist: tensorboard; extra == "dev"
 Requires-Dist: Jinja2; extra == "dev"
 Requires-Dist: peft>=0.6.0; extra == "dev"
 Requires-Dist: hf-doc-builder>=0.3.0; extra == "dev"
-Requires-Dist: torch>=1.4; extra == "dev"
+Requires-Dist: torch<2.5.0,>=1.4; extra == "dev"
 Requires-Dist: accelerate>=0.31.0; extra == "dev"
 Requires-Dist: jax>=0.4.1; extra == "dev"
 Requires-Dist: jaxlib>=0.4.1; extra == "dev"
@@ -178,7 +178,7 @@ Generating outputs is super easy with 🤗 Diffusers. To generate an image from
 from diffusers import DiffusionPipeline
 import torch
 
-pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
+pipeline = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16)
 pipeline.to("cuda")
 pipeline("An image of a squirrel in Picasso style").images[0]
 ```
@@ -249,7 +249,7 @@ Also, say 👋 in our public Discord channel <a href="https://discord.gg/G7tWnz9
   <tr style="border-top: 2px solid black">
     <td>Text-to-Image</td>
     <td><a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/text2img">Stable Diffusion Text-to-Image</a></td>
-      <td><a href="https://huggingface.co/runwayml/stable-diffusion-v1-5"> runwayml/stable-diffusion-v1-5 </a></td>
+      <td><a href="https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5"> stable-diffusion-v1-5/stable-diffusion-v1-5 </a></td>
   </tr>
   <tr>
     <td>Text-to-Image</td>
@@ -279,7 +279,7 @@ Also, say 👋 in our public Discord channel <a href="https://discord.gg/G7tWnz9
   <tr>
     <td>Text-guided Image-to-Image</td>
     <td><a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/img2img">Stable Diffusion Image-to-Image</a></td>
-      <td><a href="https://huggingface.co/runwayml/stable-diffusion-v1-5"> runwayml/stable-diffusion-v1-5 </a></td>
+      <td><a href="https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5"> stable-diffusion-v1-5/stable-diffusion-v1-5 </a></td>
   </tr>
   <tr style="border-top: 2px solid black">
     <td>Text-guided Image Inpainting</td>
@@ -307,6 +307,7 @@ Also, say 👋 in our public Discord channel <a href="https://discord.gg/G7tWnz9
 
 - https://github.com/microsoft/TaskMatrix
 - https://github.com/invoke-ai/InvokeAI
+- https://github.com/InstantID/InstantID
 - https://github.com/apple/ml-stable-diffusion
 - https://github.com/Sanster/lama-cleaner
 - https://github.com/IDEA-Research/Grounded-Segment-Anything

{diffusers-0.30.2 → diffusers-0.31.0}/README.md

@@ -73,7 +73,7 @@ Generating outputs is super easy with 🤗 Diffusers. To generate an image from
 from diffusers import DiffusionPipeline
 import torch
 
-pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
+pipeline = DiffusionPipeline.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", torch_dtype=torch.float16)
 pipeline.to("cuda")
 pipeline("An image of a squirrel in Picasso style").images[0]
 ```
@@ -144,7 +144,7 @@ Also, say 👋 in our public Discord channel <a href="https://discord.gg/G7tWnz9
   <tr style="border-top: 2px solid black">
     <td>Text-to-Image</td>
     <td><a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/text2img">Stable Diffusion Text-to-Image</a></td>
-      <td><a href="https://huggingface.co/runwayml/stable-diffusion-v1-5"> runwayml/stable-diffusion-v1-5 </a></td>
+      <td><a href="https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5"> stable-diffusion-v1-5/stable-diffusion-v1-5 </a></td>
   </tr>
   <tr>
     <td>Text-to-Image</td>
@@ -174,7 +174,7 @@ Also, say 👋 in our public Discord channel <a href="https://discord.gg/G7tWnz9
   <tr>
     <td>Text-guided Image-to-Image</td>
     <td><a href="https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/img2img">Stable Diffusion Image-to-Image</a></td>
-      <td><a href="https://huggingface.co/runwayml/stable-diffusion-v1-5"> runwayml/stable-diffusion-v1-5 </a></td>
+      <td><a href="https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5"> stable-diffusion-v1-5/stable-diffusion-v1-5 </a></td>
   </tr>
   <tr style="border-top: 2px solid black">
     <td>Text-guided Image Inpainting</td>
@@ -202,6 +202,7 @@ Also, say 👋 in our public Discord channel <a href="https://discord.gg/G7tWnz9
 
 - https://github.com/microsoft/TaskMatrix
 - https://github.com/invoke-ai/InvokeAI
+- https://github.com/InstantID/InstantID
 - https://github.com/apple/ml-stable-diffusion
 - https://github.com/Sanster/lama-cleaner
 - https://github.com/IDEA-Research/Grounded-Segment-Anything

{diffusers-0.30.2 → diffusers-0.31.0}/setup.py

@@ -130,7 +130,7 @@ _deps = [
     "regex!=2019.12.17",
     "requests",
     "tensorboard",
-    "torch>=1.4",
+    "torch>=1.4,<2.5.0",
     "torchvision",
     "transformers>=4.41.2",
     "urllib3<=2.0.0",
@@ -254,7 +254,7 @@ version_range_max = max(sys.version_info[1], 10) + 1
 
 setup(
     name="diffusers",
-    version="0.30.2",  # expected format is one of x.y.z.dev0, or x.y.z.rc1 or x.y.z (no to dashes, yes to dots)
+    version="0.31.0",  # expected format is one of x.y.z.dev0, or x.y.z.rc1 or x.y.z (no to dashes, yes to dots)
     description="State-of-the-art diffusion in PyTorch and JAX.",
     long_description=open("README.md", "r", encoding="utf-8").read(),
     long_description_content_type="text/markdown",

{diffusers-0.30.2 → diffusers-0.31.0}/src/diffusers/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "0.30.2"
+__version__ = "0.31.0"
 
 from typing import TYPE_CHECKING
 
@@ -31,6 +31,7 @@ _import_structure = {
     "loaders": ["FromOriginalModelMixin"],
     "models": [],
     "pipelines": [],
+    "quantizers.quantization_config": ["BitsAndBytesConfig"],
     "schedulers": [],
     "utils": [
         "OptionalDependencyNotAvailable",
@@ -84,10 +85,13 @@ else:
             "AutoencoderOobleck",
             "AutoencoderTiny",
             "CogVideoXTransformer3DModel",
+            "CogView3PlusTransformer2DModel",
             "ConsistencyDecoderVAE",
             "ControlNetModel",
             "ControlNetXSAdapter",
             "DiTTransformer2DModel",
+            "FluxControlNetModel",
+            "FluxMultiControlNetModel",
             "FluxTransformer2DModel",
             "HunyuanDiT2DControlNetModel",
             "HunyuanDiT2DModel",
@@ -121,7 +125,6 @@ else:
             "VQModel",
         ]
     )
-
     _import_structure["optimization"] = [
         "get_constant_schedule",
         "get_constant_schedule_with_warmup",
@@ -153,6 +156,7 @@ else:
             "StableDiffusionMixin",
         ]
     )
+    _import_structure["quantizers"] = ["DiffusersQuantizer"]
     _import_structure["schedulers"].extend(
         [
             "AmusedScheduler",
@@ -243,6 +247,7 @@ else:
             "AnimateDiffPipeline",
             "AnimateDiffSDXLPipeline",
             "AnimateDiffSparseControlNetPipeline",
+            "AnimateDiffVideoToVideoControlNetPipeline",
             "AnimateDiffVideoToVideoPipeline",
             "AudioLDM2Pipeline",
             "AudioLDM2ProjectionModel",
@@ -252,8 +257,17 @@ else:
             "BlipDiffusionControlNetPipeline",
             "BlipDiffusionPipeline",
             "CLIPImageProjection",
+            "CogVideoXFunControlPipeline",
+            "CogVideoXImageToVideoPipeline",
             "CogVideoXPipeline",
+            "CogVideoXVideoToVideoPipeline",
+            "CogView3PlusPipeline",
             "CycleDiffusionPipeline",
+            "FluxControlNetImg2ImgPipeline",
+            "FluxControlNetInpaintPipeline",
+            "FluxControlNetPipeline",
+            "FluxImg2ImgPipeline",
+            "FluxInpaintPipeline",
             "FluxPipeline",
             "HunyuanDiTControlNetPipeline",
             "HunyuanDiTPAGPipeline",
@@ -308,6 +322,7 @@ else:
             "StableCascadeCombinedPipeline",
             "StableCascadeDecoderPipeline",
             "StableCascadePriorPipeline",
+            "StableDiffusion3ControlNetInpaintingPipeline",
             "StableDiffusion3ControlNetPipeline",
             "StableDiffusion3Img2ImgPipeline",
             "StableDiffusion3InpaintPipeline",
@@ -317,6 +332,7 @@ else:
             "StableDiffusionAttendAndExcitePipeline",
             "StableDiffusionControlNetImg2ImgPipeline",
             "StableDiffusionControlNetInpaintPipeline",
+            "StableDiffusionControlNetPAGInpaintPipeline",
             "StableDiffusionControlNetPAGPipeline",
             "StableDiffusionControlNetPipeline",
             "StableDiffusionControlNetXSPipeline",
@@ -332,6 +348,7 @@ else:
             "StableDiffusionLatentUpscalePipeline",
             "StableDiffusionLDM3DPipeline",
             "StableDiffusionModelEditingPipeline",
+            "StableDiffusionPAGImg2ImgPipeline",
             "StableDiffusionPAGPipeline",
             "StableDiffusionPanoramaPipeline",
             "StableDiffusionParadigmsPipeline",
@@ -343,6 +360,7 @@ else:
             "StableDiffusionXLAdapterPipeline",
             "StableDiffusionXLControlNetImg2ImgPipeline",
             "StableDiffusionXLControlNetInpaintPipeline",
+            "StableDiffusionXLControlNetPAGImg2ImgPipeline",
             "StableDiffusionXLControlNetPAGPipeline",
             "StableDiffusionXLControlNetPipeline",
             "StableDiffusionXLControlNetXSPipeline",
@@ -521,6 +539,7 @@ else:
 
 if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
     from .configuration_utils import ConfigMixin
+    from .quantizers.quantization_config import BitsAndBytesConfig
 
     try:
         if not is_onnx_available():
@@ -545,10 +564,13 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             AutoencoderOobleck,
             AutoencoderTiny,
             CogVideoXTransformer3DModel,
+            CogView3PlusTransformer2DModel,
             ConsistencyDecoderVAE,
             ControlNetModel,
             ControlNetXSAdapter,
             DiTTransformer2DModel,
+            FluxControlNetModel,
+            FluxMultiControlNetModel,
             FluxTransformer2DModel,
             HunyuanDiT2DControlNetModel,
             HunyuanDiT2DModel,
@@ -612,6 +634,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             ScoreSdeVePipeline,
             StableDiffusionMixin,
         )
+        from .quantizers import DiffusersQuantizer
         from .schedulers import (
             AmusedScheduler,
             CMStochasticIterativeScheduler,
@@ -684,6 +707,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             AnimateDiffPipeline,
             AnimateDiffSDXLPipeline,
             AnimateDiffSparseControlNetPipeline,
+            AnimateDiffVideoToVideoControlNetPipeline,
             AnimateDiffVideoToVideoPipeline,
             AudioLDM2Pipeline,
             AudioLDM2ProjectionModel,
@@ -691,8 +715,17 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             AudioLDMPipeline,
             AuraFlowPipeline,
             CLIPImageProjection,
+            CogVideoXFunControlPipeline,
+            CogVideoXImageToVideoPipeline,
             CogVideoXPipeline,
+            CogVideoXVideoToVideoPipeline,
+            CogView3PlusPipeline,
             CycleDiffusionPipeline,
+            FluxControlNetImg2ImgPipeline,
+            FluxControlNetInpaintPipeline,
+            FluxControlNetPipeline,
+            FluxImg2ImgPipeline,
+            FluxInpaintPipeline,
             FluxPipeline,
             HunyuanDiTControlNetPipeline,
             HunyuanDiTPAGPipeline,
@@ -756,6 +789,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             StableDiffusionAttendAndExcitePipeline,
             StableDiffusionControlNetImg2ImgPipeline,
             StableDiffusionControlNetInpaintPipeline,
+            StableDiffusionControlNetPAGInpaintPipeline,
             StableDiffusionControlNetPAGPipeline,
             StableDiffusionControlNetPipeline,
             StableDiffusionControlNetXSPipeline,
@@ -771,6 +805,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             StableDiffusionLatentUpscalePipeline,
             StableDiffusionLDM3DPipeline,
             StableDiffusionModelEditingPipeline,
+            StableDiffusionPAGImg2ImgPipeline,
             StableDiffusionPAGPipeline,
             StableDiffusionPanoramaPipeline,
             StableDiffusionParadigmsPipeline,
@@ -782,6 +817,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             StableDiffusionXLAdapterPipeline,
             StableDiffusionXLControlNetImg2ImgPipeline,
             StableDiffusionXLControlNetInpaintPipeline,
+            StableDiffusionXLControlNetPAGImg2ImgPipeline,
             StableDiffusionXLControlNetPAGPipeline,
             StableDiffusionXLControlNetPipeline,
             StableDiffusionXLControlNetXSPipeline,

{diffusers-0.30.2 → diffusers-0.31.0}/src/diffusers/configuration_utils.py

@@ -510,6 +510,9 @@ class ConfigMixin:
         # remove private attributes
         config_dict = {k: v for k, v in config_dict.items() if not k.startswith("_")}
 
+        # remove quantization_config
+        config_dict = {k: v for k, v in config_dict.items() if k != "quantization_config"}
+
         # 3. Create keyword arguments that will be passed to __init__ from expected keyword arguments
         init_dict = {}
         for key in expected_keys:
@@ -586,10 +589,19 @@ class ConfigMixin:
                 value = value.as_posix()
             return value
 
+        if "quantization_config" in config_dict:
+            config_dict["quantization_config"] = (
+                config_dict.quantization_config.to_dict()
+                if not isinstance(config_dict.quantization_config, dict)
+                else config_dict.quantization_config
+            )
+
         config_dict = {k: to_json_saveable(v) for k, v in config_dict.items()}
         # Don't save "_ignore_files" or "_use_default_values"
         config_dict.pop("_ignore_files", None)
         config_dict.pop("_use_default_values", None)
+        # pop the `_pre_quantization_dtype` as torch.dtypes are not serializable.
+        _ = config_dict.pop("_pre_quantization_dtype", None)
 
         return json.dumps(config_dict, indent=2, sort_keys=True) + "\n"
 

{diffusers-0.30.2 → diffusers-0.31.0}/src/diffusers/dependency_versions_table.py

@@ -38,7 +38,7 @@ deps = {
     "regex": "regex!=2019.12.17",
     "requests": "requests",
     "tensorboard": "tensorboard",
-    "torch": "torch>=1.4",
+    "torch": "torch>=1.4,<2.5.0",
     "torchvision": "torchvision",
     "transformers": "transformers>=4.41.2",
     "urllib3": "urllib3<=2.0.0",