feat(nodes): add freeu support

Add support for FreeU. See:
- https://huggingface.co/docs/diffusers/main/en/using-diffusers/freeu
- https://github.com/ChenyangSi/FreeU

Implementation:
- `ModelPatcher.apply_freeu()` handles the enabling freeu (which is very simple with diffusers).
- `FreeUConfig` model added to hold the hyperparameters.
- `freeu_config` added as optional sub-field on `UNetField`.
- `FreeUInvocation` added, works like LoRA - chain it to add the FreeU config to the UNet
- No support for model-dependent presets, this will be a future workflow editor enhancement

Closes #4845

invokeai/backend/model_management/lora.py

@@ -12,6 +12,8 @@ from diffusers.models import UNet2DConditionModel
 from safetensors.torch import load_file
 from transformers import CLIPTextModel, CLIPTokenizer
 
+from invokeai.app.invocations.shared import FreeUConfig
+
 from .models.lora import LoRAModel
 
 """
@@ -231,6 +233,25 @@ class ModelPatcher:
             while len(skipped_layers) > 0:
                 text_encoder.text_model.encoder.layers.append(skipped_layers.pop())
 
+    @classmethod
+    @contextmanager
+    def apply_freeu(
+        cls,
+        unet: UNet2DConditionModel,
+        freeu_config: Optional[FreeUConfig] = None,
+    ):
+        did_apply_freeu = False
+        try:
+            if freeu_config is not None:
+                unet.enable_freeu(b1=freeu_config.b1, b2=freeu_config.b2, s1=freeu_config.s1, s2=freeu_config.s2)
+                did_apply_freeu = True
+
+            yield
+
+        finally:
+            if did_apply_freeu:
+                unet.disable_freeu()
+
 
 class TextualInversionModel:
     embedding: torch.Tensor  # [n, 768]|[n, 1280]