diff --git a/stacks/comfyui/compose.yaml b/stacks/comfyui/compose.yaml index 44a455a..4914bdb 100644 --- a/stacks/comfyui/compose.yaml +++ b/stacks/comfyui/compose.yaml @@ -51,7 +51,12 @@ services: # (~8.7 GB) instead of upcasting the fp8 file to fp16 (~16 GB). Matches # the box's Ampere-fp8 posture; the encoder runs once per gen so the # upcast-on-compute cost is negligible. - - COMFY_CMDLINE_EXTRA=--disable-cuda-malloc --fp8_e4m3fn-text-enc + # --use-sage-attention — 0.24.1's NATIVE attention selection (the node-based + # BlehGlobalSageAttention is dead on 0.24.1: "does not support the new + # ComfyUI attention changes"). Binds the in-image sageattention v2.2.0 + # sm_86 build (rebuilt against the pinned torch 2.12.1). Global speedup + # across Flux/SDXL/Wan (comfy-dev benchmarking, 2026-06-18). + - COMFY_CMDLINE_EXTRA=--disable-cuda-malloc --fp8_e4m3fn-text-enc --use-sage-attention volumes: - ${COMFYUI_BASEDIR}:/basedir # models/ overlaid from storetank. The ~325 GB model tree was migrated