cache-ram: lower thresholds (#14089)

Use the RAM right up to the wire as the community is bit accustomed too.

This trades off headroom for the case where large chunky intermediates
arrive and potenitally hits pagefile/swap, but a lot of people have
"it just fits" workflows out there, so strike a compromise with
75->90%.

Disable the incative cache for all but the very high RAM users.

comfy/cli_args.py

@@ -111,7 +111,7 @@ parser.add_argument("--preview-method", type=LatentPreviewMethod, default=Latent
 parser.add_argument("--preview-size", type=int, default=512, help="Sets the maximum preview size for sampler nodes.")
 
 cache_group = parser.add_mutually_exclusive_group()
-cache_group.add_argument("--cache-ram", nargs='*', type=float, default=[], metavar="GB", help="Use RAM pressure caching with the specified headroom thresholds. This is the default caching mode. The first value sets the active-cache threshold; the optional second value sets the inactive-cache/pin threshold. Defaults when no values are provided: active 25%% of system RAM (min 4GB, max 32GB), inactive 75%% of system RAM (min 12GB, max 96GB).")
+cache_group.add_argument("--cache-ram", nargs='*', type=float, default=[], metavar="GB", help="Use RAM pressure caching with the specified headroom thresholds. This is the default caching mode. The first value sets the active-cache threshold; the optional second value sets the inactive-cache/pin threshold. Defaults when no values are provided: active 10%% of system RAM (min 2GB, max 10GB), inactive 100%% of system RAM (max 96GB).")
 cache_group.add_argument("--cache-classic", action="store_true", help="Use the old style (aggressive) caching.")
 cache_group.add_argument("--cache-lru", type=int, default=0, help="Use LRU caching with a maximum of N node results cached. May use more RAM/VRAM.")
 cache_group.add_argument("--cache-none", action="store_true", help="Reduced RAM/VRAM usage at the expense of executing every node for each run.")

main.py

@@ -286,8 +286,8 @@ def prompt_worker(q, server_instance):
     cache_ram = 0
     cache_ram_inactive = 0
     if not args.cache_classic and not args.cache_none and args.cache_lru <= 0:
-        cache_ram = min(32.0, max(4.0, comfy.model_management.total_ram * 0.25 / 1024.0))
-        cache_ram_inactive = min(96.0, max(12.0, comfy.model_management.total_ram * 0.75 / 1024.0))
+        cache_ram = min(10.0, max(2.0, comfy.model_management.total_ram * 0.10 / 1024.0))
+        cache_ram_inactive = min(96.0, comfy.model_management.total_ram / 1024.0)
         if len(args.cache_ram) > 0:
             cache_ram = args.cache_ram[0]
         if len(args.cache_ram) > 1: