You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: invokeai/frontend/web/src/services/api/schema.ts
+2-3Lines changed: 2 additions & 3 deletions
Original file line number
Diff line number
Diff line change
@@ -11991,7 +11991,7 @@ export type components = {
11991
11991
* vram: DEPRECATED: This setting is no longer used. It has been replaced by `max_cache_vram_gb`, but most users will not need to use this config since automatic cache size limits should work well in most cases. This config setting will be removed once the new model cache behavior is stable.
11992
11992
* lazy_offload: DEPRECATED: This setting is no longer used. Lazy-offloading is enabled by default. This config setting will be removed once the new model cache behavior is stable.
11993
11993
* pytorch_cuda_alloc_conf: Configure the Torch CUDA memory allocator. This will impact peak reserved VRAM usage and performance. Setting to "backend:cudaMallocAsync" works well on many systems. The optimal configuration is highly dependent on the system configuration (device type, VRAM, CUDA driver version, etc.), so must be tuned experimentally.
11994
-
* device: Preferred execution device. `auto` will choose the device depending on the hardware platform and the installed torch capabilities.<br>Valid values: `auto`, `cpu`, `cuda`, `cuda:1`, `mps`
11994
+
* device: Preferred execution device. `auto` will choose the device depending on the hardware platform and the installed torch capabilities.<br>Valid values: `auto`, `cpu`, `cuda`, `mps`, `cuda:N` (where N is a device number)
11995
11995
* precision: Floating point precision. `float16` will consume half the memory of `float32` but produce slightly lower-quality images. The `auto` setting will guess the proper precision based on your video card and operating system.<br>Valid values: `auto`, `float16`, `bfloat16`, `float32`
11996
11996
* sequential_guidance: Whether to calculate guidance in serial instead of in parallel, lowering memory requirements.
* @description Floating point precision. `float16` will consume half the memory of `float32` but produce slightly lower-quality images. The `auto` setting will guess the proper precision based on your video card and operating system.
0 commit comments