Add spatial batching to latent upscale

This commit is contained in:
2026-09-03 15:12:42 +00:00
parent 2cb3c694f0
commit 36d9f4369c
5 changed files with 131 additions and 8 deletions
+2
View File
@@ -1163,6 +1163,7 @@ What this really means:
- the sampled latent is upscaled in latent space to the target size
- the conditioning is rebuilt at that target size
- the node then runs a short refinement pass over the upscaled latent with the sampler, scheduler, step count, denoise, and megapixel target you picked on the latent-upscale params node
- if the target is larger than the spatial tile size, that refinement pass is processed in spatial batches using the same tile defaults as the upstream latent-split node
Good starting point:
@@ -1170,6 +1171,7 @@ Good starting point:
- use the interpolation mode when you want a cheaper resize-only path
- start with `euler_ancestral`, `simple`, `2` steps, and `0.2` denoise
- leave width and height at `0` unless you want an exact override; otherwise `megapixels` drives the target size
- leave the spatial tile inputs at their defaults first: `512x512` tiles, `64` overlap, `0` fade width, `earlier` overlap mode
The important part is that this stage is still a latent pass, not a pixel-space resize: