Add CFG Rescale option for supporting zero-terminal SNR models (#4335)

* add support for CFG rescale

* fix typo

* move rescale position and tweak docs

* move input position

* implement suggestions from github and discord

* cleanup unused code

* add back dropped FieldDescription

* fix(ui): revert unrelated UI changes

* chore(nodes): bump denoise_latents version 1.4.0 -> 1.5.0

* feat(nodes): add cfg_rescale_multiplier to metadata node

* feat(ui): add cfg rescale multiplier to linear UI

- add param to state
- update graph builders
- add UI under advanced
- add metadata handling & recall
- regen types

* chore: black

* fix(backend): make `StableDiffusionGeneratorPipeline._rescale_cfg()` staticmethod

This doesn't need access to class.

* feat(backend): add docstring for `_rescale_cfg()` method

* feat(ui): update cfg rescale mult translation string

---------

Co-authored-by: psychedelicious <4822129+psychedelicious@users.noreply.github.com>

invokeai/app/invocations/latent.py

@@ -215,7 +215,7 @@ def get_scheduler(
     title="Denoise Latents",
     tags=["latents", "denoise", "txt2img", "t2i", "t2l", "img2img", "i2i", "l2l"],
     category="latents",
-    version="1.4.0",
+    version="1.5.0",
 )
 class DenoiseLatentsInvocation(BaseInvocation):
     """Denoises noisy latents to decodable images"""
@@ -273,6 +273,9 @@ class DenoiseLatentsInvocation(BaseInvocation):
         input=Input.Connection,
         ui_order=7,
     )
+    cfg_rescale_multiplier: float = InputField(
+        default=0, ge=0, lt=1, description=FieldDescriptions.cfg_rescale_multiplier
+    )
     latents: Optional[LatentsField] = InputField(
         default=None,
         description=FieldDescriptions.latents,
@@ -332,6 +335,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
             unconditioned_embeddings=uc,
             text_embeddings=c,
             guidance_scale=self.cfg_scale,
+            guidance_rescale_multiplier=self.cfg_rescale_multiplier,
             extra=extra_conditioning_info,
             postprocessing_settings=PostprocessingSettings(
                 threshold=0.0,  # threshold,