Clarify flux2klein fp8 nightly handoff

benchmarks/flux2klein/overnight-state.json

@@ -1,7 +1,7 @@
 {
-  "testsSet": true,
+  "testsSet": false,
   "serverBusy": false,
-  "reason": "Overnight flux2klein smoke test submitted successfully.",
+  "reason": "Could not verify queue state: connection timed out.",
   "cases": [
     {
       "workflow": "models/flux2klein/image-edit-9b-distilled/workflow.json",
@@ -26,9 +26,8 @@
   ],
   "reviewPending": false,
   "verdict": "Keep the 2026-08-28 single-image smoke as the benchmark winner for now; identity and background stayed clean, but queue one more smoke test before broader promotion.",
-  "date": "2026-08-28T02:09:03.591Z",
+  "date": "2026-08-30T02:04:46.554Z",
   "optimizedPaths": [
-    "optimized/image-edit/flux2klein-9b-fp8-edit-master/README.md",
-    "optimized/image-edit/zimage-turbo-3070-inpaint-start/README.md"
+    "optimized/notes/flux2klein.md"
   ]
 }

optimized/notes/flux2klein.md

@@ -28,6 +28,7 @@
 
 - Prefer official Comfy templates as the baseline unless a community workflow clearly improves something real.
 - For `9B`, watch closely for text-encoder mismatches.
+- Keep the maintained `9B fp8` master pinned to the literal `flux-2-klein-9b-fp8.safetensors` filename; the imported distilled template still shows `fp8mixed` in the widget value, so do not copy that label back into the maintained graph.
 - Community `9B` optimization notes often revolve around:
   - low-step usage
   - `CFG=1`