Changing ImageToLatentsInvocation node to default to detected precision (#3838)

## What type of PR is this? (check all applicable)

- [ ] Refactor
- [ ] Feature
- [X] Bug Fix
- [ ] Optimization
- [ ] Documentation Update


## Have you discussed this change with the InvokeAI team?
- [X] Yes
- [ ] No, because:

      
## Description
ImageToLatentsInvocation defaulted to float16 rather than detect the
requested precision from configs.
This caused an exception to be raised on systems that don't support
float16 (e.g. CPU).


## Related Tickets & Documents

<!--
For pull requests that relate or close an issue, please include them
below. 

For example having the text: "closes #1234" would connect the current
pull
request to issue 1234.  And when we merge the pull request, Github will
automatically close the issue.
-->

- Related Issue #
- Closes #

## QA Instructions, Screenshots, Recordings

<!-- 
Please provide steps on how to test changes, any hardware or 
software specifications as well as any other pertinent information. 
-->

## Added/updated tests?

- [ ] Yes
- [x] No : _please replace this line with details on why tests
      have not been included_

## [optional] Are there any post deployment tasks we need to perform?

invokeai/app/invocations/latent.py

@@ -22,7 +22,7 @@ from ...backend.stable_diffusion.diffusers_pipeline import (
 from ...backend.stable_diffusion.diffusion.shared_invokeai_diffusion import \
     PostprocessingSettings
 from ...backend.stable_diffusion.schedulers import SCHEDULER_MAP
-from ...backend.util.devices import choose_torch_device, torch_dtype
+from ...backend.util.devices import choose_torch_device, torch_dtype, choose_precision
 from ..models.image import ImageCategory, ImageField, ResourceOrigin
 from .baseinvocation import (BaseInvocation, BaseInvocationOutput,
                              InvocationConfig, InvocationContext)
@@ -38,6 +38,10 @@ from diffusers.models.attention_processor import (
     XFormersAttnProcessor,
 )
 
+
+DEFAULT_PRECISION = choose_precision(choose_torch_device())
+
+
 class LatentsField(BaseModel):
     """A latents field used for passing latents between invocations"""
 
@@ -492,7 +496,7 @@ class LatentsToImageInvocation(BaseInvocation):
     tiled: bool = Field(
         default=False,
         description="Decode latents by overlaping tiles(less memory consumption)")
-    fp32: bool = Field(False, description="Decode in full precision")
+    fp32: bool = Field(DEFAULT_PRECISION=='float32', description="Decode in full precision")
     metadata: Optional[CoreMetadata] = Field(default=None, description="Optional core metadata to be written to the image")
 
     # Schema customisation
@@ -686,7 +690,7 @@ class ImageToLatentsInvocation(BaseInvocation):
     tiled: bool = Field(
         default=False,
         description="Encode latents by overlaping tiles(less memory consumption)")
-    fp32: bool = Field(False, description="Decode in full precision")
+    fp32: bool = Field(DEFAULT_PRECISION=='float32', description="Decode in full precision")
 
 
     # Schema customisation