mirror of
https://github.com/tangerineturtle1/NX2navi.git
synced 2026-11-19 10:49:58 -04:00
Run the smaller render sizes of a DLSS mode on that mode's feature, with the history kept.
Each render size had a DLSS feature of its own, so a step of dynamic resolution or a screen at another share cost a feature creation and a new history. The feature created at the render size of the DLSS mode set now also takes every smaller render size that DLSS reports for its output size and quality value (the optimal settings callback's dynamic minimum), as the sub-rectangle of that frame's own images. A size above the feature's own, below the minimum, of another shape or output size, or met under another mode still gets its own feature, and a refused evaluation turns the sharing off for the run. The first frame of another size is still left out of the per-object motion pass and still starts frame generation anew. The setting is dlss_range (NX2NAVI_DLSS_RANGE), 1 by default: a run whose render size never changes creates and evaluates its feature with the parameters it had, and adds one query after the creation. The log says for each feature which render sizes it takes, and the status line counts the changes of size that kept the history against those that made a feature. Compiled and linked only; no evaluation of a shared feature has run on a GPU. Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
This commit is contained in:
@@ -556,6 +556,12 @@
|
||||
# 0: none is ever freed (about 0.5 GB more video memory after the first pause). 2: as 1, and the networks that stay
|
||||
# are not made again when another is made (shows striped pause screens; for tests).
|
||||
# dlss_idle_free = 1
|
||||
# One DLSS network for the render sizes of a DLSS mode. 1: the network made for the mode's own render size also takes
|
||||
# the smaller render sizes DLSS allows on it (dynamic resolution's steps with dyn_res = 1, a screen that renders
|
||||
# smaller than play), so a change of size makes no new network and keeps the picture DLSS has built up. 0: every
|
||||
# render size has its own network and starts its picture anew. The log says for each network which render sizes it
|
||||
# takes, and counts the changes of size that kept the picture against those that made a network. Read at start.
|
||||
# dlss_range = 1
|
||||
# Per-object motion vectors for DLSS: characters, animals and moving objects get their own motion instead of the
|
||||
# camera's, so DLSS keeps their history instead of smearing or rejecting it. Costs some CPU time each frame (about 1-2 ms
|
||||
# on a laptop CPU); 0 leaves camera-only motion. Read at start.
|
||||
|
||||
Reference in New Issue
Block a user