Merge branch 'main' into fix_syntax_qwenimageEditPlus

Author: SahilCarterr

.github/workflows/pr_modular_tests.yml

@@ -110,8 +110,9 @@ jobs:
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m uv pip install -e [quality,test]
-        pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
-        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
+        # Stopping this update temporarily until the Hub RC is fully shipped and integrated.
+        # pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
+        # pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
 
     - name: Environment
       run: |

.github/workflows/pr_tests.yml

@@ -116,8 +116,9 @@ jobs:
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m uv pip install -e [quality,test]
-        pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
-        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
+        # Stopping this update temporarily until the Hub RC is fully shipped and integrated.
+        # pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
+        # pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
 
     - name: Environment
       run: |
@@ -253,9 +254,10 @@ jobs:
         python -m uv pip install -e [quality,test]
         # TODO (sayakpaul, DN6): revisit `--no-deps`
         python -m pip install -U peft@git+https://github.com/huggingface/peft.git --no-deps
-        python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
-        python -m uv pip install -U tokenizers
-        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
+        # Stopping this update temporarily until the Hub RC is fully shipped and integrated.
+        # python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
+        # python -m uv pip install -U tokenizers
+        # pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
 
     - name: Environment
       run: |

.github/workflows/pr_tests_gpu.yml

@@ -132,8 +132,9 @@ jobs:
         run: |
           python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
           python -m uv pip install -e [quality,test]
-          pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-          pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
+          # Stopping this update temporarily until the Hub RC is fully shipped and integrated.
+          # pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+          # pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
 
       - name: Environment
         run: |
@@ -203,8 +204,9 @@ jobs:
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m uv pip install -e [quality,test]
         python -m uv pip install peft@git+https://github.com/huggingface/peft.git
-        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-        pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
+        # Stopping this update temporarily until the Hub RC is fully shipped and integrated.
+        # pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+        # pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
 
     - name: Environment
       run: |
@@ -266,7 +268,8 @@ jobs:
     - name: Install dependencies
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
+        # Stopping this update temporarily until the Hub RC is fully shipped and integrated.
+        # pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
         python -m uv pip install -e [quality,test,training]
 
     - name: Environment

docs/source/en/optimization/attention_backends.md

@@ -11,7 +11,7 @@ specific language governing permissions and limitations under the License. -->
 
 # Attention backends
 
-> [!TIP]
+> [!NOTE]
 > The attention dispatcher is an experimental feature. Please open an issue if you have any feedback or encounter any problems.
 
 Diffusers provides several optimized attention algorithms that are more memory and computationally efficient through it's *attention dispatcher*. The dispatcher acts as a router for managing and switching between different attention implementations and provides a unified interface for interacting with them.
@@ -33,7 +33,7 @@ The [`~ModelMixin.set_attention_backend`] method iterates through all the module
 
 The example below demonstrates how to enable the `_flash_3_hub` implementation for FlashAttention-3 from the [kernel](https://github.com/huggingface/kernels) library, which allows you to instantly use optimized compute kernels from the Hub without requiring any setup.
 
-> [!TIP]
+> [!NOTE]
 > FlashAttention-3 is not supported for non-Hopper architectures, in which case, use FlashAttention with `set_attention_backend("flash")`.
 
 ```py
@@ -78,10 +78,16 @@ with attention_backend("_flash_3_hub"):
     image = pipeline(prompt).images[0]
 ```
 
+> [!TIP]
+> Most attention backends support `torch.compile` without graph breaks and can be used to further speed up inference.
+
 ## Available backends
 
 Refer to the table below for a complete list of available attention backends and their variants.
 
+<details>
+<summary>Expand</summary>
+
 | Backend Name | Family | Description |
 |--------------|--------|-------------|
 | `native` | [PyTorch native](https://docs.pytorch.org/docs/stable/generated/torch.nn.attention.SDPBackend.html#torch.nn.attention.SDPBackend) | Default backend using PyTorch's scaled_dot_product_attention |
@@ -104,3 +110,5 @@ Refer to the table below for a complete list of available attention backends and
 | `_sage_qk_int8_pv_fp16_cuda` | [SageAttention](https://github.com/thu-ml/SageAttention) | INT8 QK + FP16 PV (CUDA) |
 | `_sage_qk_int8_pv_fp16_triton` | [SageAttention](https://github.com/thu-ml/SageAttention) | INT8 QK + FP16 PV (Triton) |
 | `xformers` | [xFormers](https://github.com/facebookresearch/xformers) | Memory-efficient attention |
+
+</details>

setup.py

@@ -102,7 +102,8 @@
     "filelock",
     "flax>=0.4.1",
     "hf-doc-builder>=0.3.0",
-    "huggingface-hub>=0.34.0",
+    "httpx<1.0.0",
+    "huggingface-hub>=0.34.0,<2.0",
     "requests-mock==1.10.0",
     "importlib_metadata",
     "invisible-watermark>=0.2.0",
@@ -259,6 +260,7 @@ def run(self):
 install_requires = [
     deps["importlib_metadata"],
     deps["filelock"],
+    deps["httpx"],
     deps["huggingface-hub"],
     deps["numpy"],
     deps["regex"],

src/diffusers/configuration_utils.py

@@ -30,11 +30,11 @@
 from huggingface_hub import DDUFEntry, create_repo, hf_hub_download
 from huggingface_hub.utils import (
     EntryNotFoundError,
+    HfHubHTTPError,
     RepositoryNotFoundError,
     RevisionNotFoundError,
     validate_hf_hub_args,
 )
-from requests import HTTPError
 from typing_extensions import Self
 
 from . import __version__
@@ -419,7 +419,7 @@ def load_config(
                 raise EnvironmentError(
                     f"{pretrained_model_name_or_path} does not appear to have a file named {cls.config_name}."
                 )
-            except HTTPError as err:
+            except HfHubHTTPError as err:
                 raise EnvironmentError(
                     "There was a specific connection error when trying to load"
                     f" {pretrained_model_name_or_path}:\n{err}"

src/diffusers/dependency_versions_table.py

@@ -9,7 +9,8 @@
     "filelock": "filelock",
     "flax": "flax>=0.4.1",
     "hf-doc-builder": "hf-doc-builder>=0.3.0",
-    "huggingface-hub": "huggingface-hub>=0.34.0",
+    "httpx": "httpx<1.0.0",
+    "huggingface-hub": "huggingface-hub>=0.34.0,<2.0",
     "requests-mock": "requests-mock==1.10.0",
     "importlib_metadata": "importlib_metadata",
     "invisible-watermark": "invisible-watermark>=0.2.0",