Add tiling to SpandrelImageToImageInvocation

[RyanJDick]

Summary

Add tiling to the SpandrelImageToImageInvocation node so that it can process large images.

Tiling enables this node to run on effectively any input image dimension. Of course, the computation time increases quadratically with the image dimension.

Some profiling results on an RTX4090:

• Input 1024x1024, 4x upscale, 4x UltraSharp ESRGAN: 13 secs, <4 GB VRAM
• Input 4096x4096, 4x upscale, 4x UltraSharop ESRGAN: 46 secs, <4 GB VRAM
• Input 4096x4096, 2x upscale, SwinIR: 165 secs, <5 GB VRAM

A lot of the time is spent PNG encoding the final image:

• PNG encoding of a 16384x16384 image takes 83secs @ pil_compress_level=7, 24secs @ pil_compress_level=1

Callout: If we want to start building workflows that pass large images between nodes, we are going to have to find a way to avoid the PNG encode/decode roundtrip that we are currently doing. As is, we will be incurring a huge penalty for every node that receives/produces a large image.

QA Instructions

• Tested with tiling up to 4096x4096 -> 16384x16384.
• Test on images with an alpha channel (the alpha channel is dropped).
• Test on images with odd dimension.
• Test no tiling (tile_size=0)

Merge Plan

• Merge Add support for Spandrel Image-to-Image models (e.g. ESRGAN, Real-ESRGAN, Swin-IR, DAT, etc.) #6556 first, and change the target branch to main.

Checklist

• The PR has a short but descriptive title, suitable for a changelog
• Tests added / updated (if applicable)
• Documentation added / updated (if applicable)

[brandonrising]

What do you think of adding something like this to the tile loop?

--- a/invokeai/app/invocations/spandrel_image_to_image.py
+++ b/invokeai/app/invocations/spandrel_image_to_image.py
@@ -14,6 +14,7 @@ from invokeai.app.invocations.fields import (
 )
 from invokeai.app.invocations.model import ModelIdentifierField
 from invokeai.app.invocations.primitives import ImageOutput
+from invokeai.app.services.session_processor.session_processor_common import CanceledException
 from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.backend.spandrel_image_to_image_model import SpandrelImageToImageModel
 from invokeai.backend.tiles.tiles import calc_tiles_min_overlap
@@ -104,6 +105,9 @@ class SpandrelImageToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
             image_tensor = image_tensor.to(device=spandrel_model.device, dtype=spandrel_model.dtype)

             for tile, scaled_tile in tqdm(list(zip(tiles, scaled_tiles, strict=True)), desc="Upscaling Tiles"):
+                if context.util.is_canceled():
+                    raise CanceledException
+
                 # Extract the current tile from the input tensor.
                 input_tile = image_tensor[
                     :, :, tile.coords.top : tile.coords.bottom, tile.coords.left : tile.coords.right