diff --git a/invokeai/app/api/routers/model_manager.py b/invokeai/app/api/routers/model_manager.py
index f67393f2ea2..81d4a927e83 100644
--- a/invokeai/app/api/routers/model_manager.py
+++ b/invokeai/app/api/routers/model_manager.py
@@ -1044,10 +1044,14 @@ class HFTokenHelper:
     @classmethod
     def get_status(cls) -> HFTokenStatus:
         try:
-            if huggingface_hub.get_token_permission(huggingface_hub.get_token()):
+            token = huggingface_hub.get_token()
+            if token is None:
+                # No token set
+                return HFTokenStatus.INVALID
+            if huggingface_hub.get_token_permission(token):
                 # Valid token!
                 return HFTokenStatus.VALID
-            # No token set
+            # Token exists but has no permissions (shouldn't normally happen)
             return HFTokenStatus.INVALID
         except Exception:
             return HFTokenStatus.UNKNOWN
diff --git a/invokeai/app/invocations/flux_text_encoder.py b/invokeai/app/invocations/flux_text_encoder.py
index 56ebbe7fd9d..580aad3286a 100644
--- a/invokeai/app/invocations/flux_text_encoder.py
+++ b/invokeai/app/invocations/flux_text_encoder.py
@@ -2,7 +2,7 @@
 from typing import Iterator, Literal, Optional, Tuple, Union
 
 import torch
-from transformers import CLIPTextModel, CLIPTokenizer, T5EncoderModel, T5Tokenizer, T5TokenizerFast
+from transformers import CLIPTextModel, CLIPTokenizer, T5EncoderModel, T5Tokenizer
 
 from invokeai.app.invocations.baseinvocation import BaseInvocation, invocation
 from invokeai.app.invocations.fields import (
@@ -86,7 +86,7 @@ def _t5_encode(self, context: InvocationContext) -> torch.Tensor:
             ExitStack() as exit_stack,
         ):
             assert isinstance(t5_text_encoder, T5EncoderModel)
-            assert isinstance(t5_tokenizer, (T5Tokenizer, T5TokenizerFast))
+            assert isinstance(t5_tokenizer, T5Tokenizer)
 
             # Determine if the model is quantized.
             # If the model is quantized, then we need to apply the LoRA weights as sidecar layers. This results in
@@ -186,7 +186,7 @@ def _t5_lora_iterator(self, context: InvocationContext) -> Iterator[Tuple[ModelP
     def _log_t5_tokenization(
         self,
         context: InvocationContext,
-        tokenizer: Union[T5Tokenizer, T5TokenizerFast],
+        tokenizer: T5Tokenizer,
     ) -> None:
         """Logs the tokenization of a prompt for a T5-based model like FLUX."""
 
diff --git a/invokeai/app/invocations/sd3_text_encoder.py b/invokeai/app/invocations/sd3_text_encoder.py
index 24647c9cfc7..e2ade1ddf93 100644
--- a/invokeai/app/invocations/sd3_text_encoder.py
+++ b/invokeai/app/invocations/sd3_text_encoder.py
@@ -8,7 +8,6 @@
     CLIPTokenizer,
     T5EncoderModel,
     T5Tokenizer,
-    T5TokenizerFast,
 )
 
 from invokeai.app.invocations.baseinvocation import BaseInvocation, invocation
@@ -102,7 +101,7 @@ def _t5_encode(self, context: InvocationContext, max_seq_len: int) -> torch.Tens
         ):
             context.util.signal_progress("Running T5 encoder")
             assert isinstance(t5_text_encoder, T5EncoderModel)
-            assert isinstance(t5_tokenizer, (T5Tokenizer, T5TokenizerFast))
+            assert isinstance(t5_tokenizer, T5Tokenizer)
 
             text_inputs = t5_tokenizer(
                 prompt,
diff --git a/invokeai/app/services/model_install/model_install_default.py b/invokeai/app/services/model_install/model_install_default.py
index 77dc3dfa70a..240757a0368 100644
--- a/invokeai/app/services/model_install/model_install_default.py
+++ b/invokeai/app/services/model_install/model_install_default.py
@@ -16,7 +16,7 @@
 
 import torch
 import yaml
-from huggingface_hub import HfFolder
+from huggingface_hub import get_token as hf_get_token
 from pydantic.networks import AnyHttpUrl
 from pydantic_core import Url
 from requests import Session
@@ -750,7 +750,7 @@ def _import_from_hf(
     ) -> ModelInstallJob:
         # Add user's cached access token to HuggingFace requests
         if source.access_token is None:
-            source.access_token = HfFolder.get_token()
+            source.access_token = hf_get_token()
         remote_files, metadata = self._remote_files_from_source(source)
         return self._import_remote_model(
             source=source,
diff --git a/invokeai/backend/image_util/safety_checker.py b/invokeai/backend/image_util/safety_checker.py
index ab09a296197..1f2acc58c56 100644
--- a/invokeai/backend/image_util/safety_checker.py
+++ b/invokeai/backend/image_util/safety_checker.py
@@ -9,7 +9,7 @@
 import numpy as np
 from diffusers.pipelines.stable_diffusion.safety_checker import StableDiffusionSafetyChecker
 from PIL import Image, ImageFilter
-from transformers import AutoFeatureExtractor
+from transformers import AutoImageProcessor
 
 import invokeai.backend.util.logging as logger
 from invokeai.app.services.config.config_default import get_config
@@ -36,14 +36,14 @@ def _load_safety_checker(cls):
         try:
             model_path = get_config().models_path / CHECKER_PATH
             if model_path.exists():
-                cls.feature_extractor = AutoFeatureExtractor.from_pretrained(model_path)
+                cls.feature_extractor = AutoImageProcessor.from_pretrained(model_path)
                 cls.safety_checker = StableDiffusionSafetyChecker.from_pretrained(model_path)
             else:
                 model_path.mkdir(parents=True, exist_ok=True)
-                cls.feature_extractor = AutoFeatureExtractor.from_pretrained(repo_id)
-                cls.feature_extractor.save_pretrained(model_path, safe_serialization=True)
+                cls.feature_extractor = AutoImageProcessor.from_pretrained(repo_id)
+                cls.feature_extractor.save_pretrained(model_path)
                 cls.safety_checker = StableDiffusionSafetyChecker.from_pretrained(repo_id)
-                cls.safety_checker.save_pretrained(model_path, safe_serialization=True)
+                cls.safety_checker.save_pretrained(model_path)
         except Exception as e:
             logger.warning(f"Could not load NSFW checker: {str(e)}")
 
diff --git a/invokeai/backend/model_manager/load/model_loaders/flux.py b/invokeai/backend/model_manager/load/model_loaders/flux.py
index 2de51a8acae..be9f6e457e2 100644
--- a/invokeai/backend/model_manager/load/model_loaders/flux.py
+++ b/invokeai/backend/model_manager/load/model_loaders/flux.py
@@ -13,7 +13,7 @@
     CLIPTextModel,
     CLIPTokenizer,
     T5EncoderModel,
-    T5TokenizerFast,
+    T5Tokenizer,
 )
 
 from invokeai.app.services.config.config_default import get_config
@@ -409,7 +409,7 @@ def _load_model(
             )
         match submodel_type:
             case SubModelType.Tokenizer2 | SubModelType.Tokenizer3:
-                return T5TokenizerFast.from_pretrained(
+                return T5Tokenizer.from_pretrained(
                     Path(config.path) / "tokenizer_2", max_length=512, local_files_only=True
                 )
             case SubModelType.TextEncoder2 | SubModelType.TextEncoder3:
@@ -437,8 +437,11 @@ def _load_state_dict_into_t5(cls, model: T5EncoderModel, state_dict: dict[str, t
         missing_keys, unexpected_keys = model.load_state_dict(state_dict, strict=False, assign=True)
         assert len(unexpected_keys) == 0
         assert set(missing_keys) == {"encoder.embed_tokens.weight"}
-        # Assert that the layers we expect to be shared are actually shared.
-        assert model.encoder.embed_tokens.weight is model.shared.weight
+        # Re-tie shared weights. In transformers 5.x, weight tying is implemented at the
+        # parameter level (via _tie_weights / tie_weights) rather than as a Python object
+        # alias.  load_state_dict(assign=True) replaces parameters in-place, which severs
+        # the parameter-level tie.  Calling tie_weights() re-establishes it.
+        model.tie_weights()
 
 
 @ModelLoaderRegistry.register(base=BaseModelType.Any, type=ModelType.T5Encoder, format=ModelFormat.T5Encoder)
@@ -455,7 +458,7 @@ def _load_model(
 
         match submodel_type:
             case SubModelType.Tokenizer2 | SubModelType.Tokenizer3:
-                return T5TokenizerFast.from_pretrained(
+                return T5Tokenizer.from_pretrained(
                     Path(config.path) / "tokenizer_2", max_length=512, local_files_only=True
                 )
             case SubModelType.TextEncoder2 | SubModelType.TextEncoder3:
diff --git a/invokeai/backend/model_manager/load/model_util.py b/invokeai/backend/model_manager/load/model_util.py
index c3477fa6603..0c6c8f7f4ab 100644
--- a/invokeai/backend/model_manager/load/model_util.py
+++ b/invokeai/backend/model_manager/load/model_util.py
@@ -10,7 +10,7 @@
 import torch
 from diffusers.pipelines.pipeline_utils import DiffusionPipeline
 from diffusers.schedulers.scheduling_utils import SchedulerMixin
-from transformers import CLIPTokenizer, PreTrainedTokenizerBase, T5Tokenizer, T5TokenizerFast
+from transformers import CLIPTokenizer, PreTrainedTokenizerBase, T5Tokenizer
 
 from invokeai.backend.image_util.depth_anything.depth_anything_pipeline import DepthAnythingPipeline
 from invokeai.backend.image_util.grounding_dino.grounding_dino_pipeline import GroundingDinoPipeline
@@ -64,10 +64,7 @@ def calc_model_size_by_data(logger: logging.Logger, model: AnyModel) -> int:
             return 0
     elif isinstance(
         model,
-        (
-            T5TokenizerFast,
-            T5Tokenizer,
-        ),
+        T5Tokenizer,
     ):
         # HACK(ryand): len(model) just returns the vocabulary size, so this is blatantly wrong. It should be small
         # relative to the text encoder that it's used with, so shouldn't matter too much, but we should fix this at some
diff --git a/invokeai/backend/model_manager/metadata/fetch/huggingface.py b/invokeai/backend/model_manager/metadata/fetch/huggingface.py
index 1b2b6c36742..0734a4e11af 100644
--- a/invokeai/backend/model_manager/metadata/fetch/huggingface.py
+++ b/invokeai/backend/model_manager/metadata/fetch/huggingface.py
@@ -16,10 +16,11 @@
 import json
 import re
 from pathlib import Path
+from types import SimpleNamespace
 from typing import Optional
 
 import requests
-from huggingface_hub import HfApi, configure_http_backend, hf_hub_url
+from huggingface_hub import HfApi, hf_hub_url
 from huggingface_hub.errors import RepositoryNotFoundError, RevisionNotFoundError
 from pydantic.networks import AnyHttpUrl
 from requests.sessions import Session
@@ -47,7 +48,7 @@ def __init__(self, session: Optional[Session] = None):
         this module without an internet connection.
         """
         self._requests = session or requests.Session()
-        configure_http_backend(backend_factory=lambda: self._requests)
+        self._has_custom_session = session is not None
 
     @classmethod
     def from_json(cls, json: str) -> HuggingFaceMetadata:
@@ -55,6 +56,30 @@ def from_json(cls, json: str) -> HuggingFaceMetadata:
         metadata = HuggingFaceMetadata.model_validate_json(json)
         return metadata
 
+    def _model_info_via_session(self, repo_id: str, variant: Optional[ModelRepoVariant] = None) -> SimpleNamespace:
+        """Fetch model info using the injected requests session (for testing/custom backends)."""
+        params = {"blobs": "true"}
+        url = f"https://huggingface.co/api/models/{repo_id}"
+        if variant is not None:
+            url += f"/revision/{variant}"
+        resp = self._requests.get(url, params=params)
+        if resp.status_code == 404:
+            error_code = resp.headers.get("X-Error-Code", "")
+            if error_code == "RevisionNotFound" or (variant is not None):
+                raise RevisionNotFoundError(f"Revision '{variant}' not found for repo '{repo_id}'.")
+            raise RepositoryNotFoundError(f"Repository '{repo_id}' not found.")
+        resp.raise_for_status()
+        data = resp.json()
+        # Convert siblings dicts to SimpleNamespace objects matching HfApi.model_info() shape
+        siblings = []
+        for s in data.get("siblings", []):
+            siblings.append(SimpleNamespace(
+                rfilename=s.get("rfilename"),
+                size=s.get("size") or (s.get("lfs", {}) or {}).get("size"),
+                lfs=s.get("lfs"),
+            ))
+        return SimpleNamespace(id=data["id"], siblings=siblings)
+
     def from_id(self, id: str, variant: Optional[ModelRepoVariant] = None) -> AnyModelRepoMetadata:
         """Return a HuggingFaceMetadata object given the model's repo_id."""
         # Little loop which tries fetching a revision corresponding to the selected variant.
@@ -67,7 +92,12 @@ def from_id(self, id: str, variant: Optional[ModelRepoVariant] = None) -> AnyMod
         repo_id = id.split("::")[0] or id
         while not model_info:
             try:
-                model_info = HfApi().model_info(repo_id=repo_id, files_metadata=True, revision=variant)
+                # Use the injected session when provided (supports testing with mock adapters).
+                # Otherwise use HfApi which uses httpx internally.
+                if self._has_custom_session:
+                    model_info = self._model_info_via_session(repo_id, variant)
+                else:
+                    model_info = HfApi().model_info(repo_id=repo_id, files_metadata=True, revision=variant)
             except RepositoryNotFoundError as excp:
                 raise UnknownMetadataException(f"'{repo_id}' not found. See trace for details.") from excp
             except RevisionNotFoundError:
diff --git a/invokeai/backend/model_manager/metadata/metadata_base.py b/invokeai/backend/model_manager/metadata/metadata_base.py
index e16ad4cbc47..b048144e547 100644
--- a/invokeai/backend/model_manager/metadata/metadata_base.py
+++ b/invokeai/backend/model_manager/metadata/metadata_base.py
@@ -17,7 +17,7 @@
 from pathlib import Path
 from typing import List, Literal, Optional, Union
 
-from huggingface_hub import configure_http_backend, hf_hub_url
+from huggingface_hub import hf_hub_url
 from pydantic import BaseModel, Field, TypeAdapter
 from pydantic.networks import AnyHttpUrl
 from requests.sessions import Session
@@ -111,7 +111,6 @@ def download_urls(
         full-precision model is returned.
         """
         session = session or Session()
-        configure_http_backend(backend_factory=lambda: session)  # used in testing
 
         paths = filter_files([x.path for x in self.files], variant, subfolder, subfolders)  #  all files in the model
 
diff --git a/invokeai/backend/quantization/scripts/quantize_t5_xxl_bnb_llm_int8.py b/invokeai/backend/quantization/scripts/quantize_t5_xxl_bnb_llm_int8.py
index 2e610404cdc..1bcb1227fe8 100644
--- a/invokeai/backend/quantization/scripts/quantize_t5_xxl_bnb_llm_int8.py
+++ b/invokeai/backend/quantization/scripts/quantize_t5_xxl_bnb_llm_int8.py
@@ -15,8 +15,11 @@ def load_state_dict_into_t5(model: T5EncoderModel, state_dict: dict):
     missing_keys, unexpected_keys = model.load_state_dict(state_dict, strict=False, assign=True)
     assert len(unexpected_keys) == 0
     assert set(missing_keys) == {"encoder.embed_tokens.weight"}
-    # Assert that the layers we expect to be shared are actually shared.
-    assert model.encoder.embed_tokens.weight is model.shared.weight
+    # Re-tie shared weights. In transformers 5.x, weight tying is implemented at the
+    # parameter level (via _tie_weights / tie_weights) rather than as a Python object
+    # alias.  load_state_dict(assign=True) replaces parameters in-place, which severs
+    # the parameter-level tie.  Calling tie_weights() re-establishes it.
+    model.tie_weights()
 
 
 def main():
diff --git a/invokeai/backend/stable_diffusion/diffusers_pipeline.py b/invokeai/backend/stable_diffusion/diffusers_pipeline.py
index de5253f0733..054e04dcb28 100644
--- a/invokeai/backend/stable_diffusion/diffusers_pipeline.py
+++ b/invokeai/backend/stable_diffusion/diffusers_pipeline.py
@@ -17,7 +17,7 @@
 from diffusers.schedulers.scheduling_utils import KarrasDiffusionSchedulers, SchedulerMixin
 from diffusers.utils.import_utils import is_xformers_available
 from pydantic import Field
-from transformers import CLIPFeatureExtractor, CLIPTextModel, CLIPTokenizer
+from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 
 from invokeai.app.services.config.config_default import get_config
 from invokeai.backend.stable_diffusion.diffusion.conditioning_data import IPAdapterData, TextConditioningData
@@ -139,7 +139,7 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
             Please, refer to the [model card](https://huggingface.co/CompVis/stable-diffusion-v1-4) for details.
-        feature_extractor ([`CLIPFeatureExtractor`]):
+        feature_extractor ([`CLIPImageProcessor`]):
             Model that extracts features from generated images to be used as inputs for the `safety_checker`.
     """
 
@@ -151,7 +151,7 @@ def __init__(
         unet: UNet2DConditionModel,
         scheduler: KarrasDiffusionSchedulers,
         safety_checker: Optional[StableDiffusionSafetyChecker],
-        feature_extractor: Optional[CLIPFeatureExtractor],
+        feature_extractor: Optional[CLIPImageProcessor],
         requires_safety_checker: bool = False,
     ):
         super().__init__(
diff --git a/pyproject.toml b/pyproject.toml
index adfe5982baf..2fac347f320 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -49,7 +49,7 @@ dependencies = [
   "torch~=2.7.0",                         # torch and related dependencies are loosely pinned, will respect requirement of `diffusers[torch]`
   "torchsde",                             # diffusers needs this for SDE solvers, but it is not an explicit dep of diffusers
   "torchvision",
-  "transformers>=4.56.0",
+  "transformers>=5.1.0",
 
   # Core application dependencies, pinned for reproducible builds.
   "fastapi-events",
@@ -123,7 +123,8 @@ dependencies = [
 [tool.uv]
 # Prevent opencv-python from ever being chosen during dependency resolution.
 # This prevents conflicts with opencv-contrib-python, which Invoke requires.
-override-dependencies = ["opencv-python; sys_platform=='never'"]
+# Force transformers>=5.1.0 past compel==2.1.1's ~=4.25 (<5.0) constraint.
+override-dependencies = ["opencv-python; sys_platform=='never'", "transformers>=5.1.0"]
 conflicts = [[{ extra = "cpu" }, { extra = "cuda" }, { extra = "rocm" }]]
 index-strategy = "unsafe-best-match"