diff --git a/.claudian/sessions/conv-1776871296744-2ksok7n1u.meta.json b/.claudian/sessions/conv-1776871296744-2ksok7n1u.meta.json
index 21aa311..007a138 100644
--- a/.claudian/sessions/conv-1776871296744-2ksok7n1u.meta.json
+++ b/.claudian/sessions/conv-1776871296744-2ksok7n1u.meta.json
@@ -4,8 +4,8 @@
   "title": "Design ComfyUI video segmentation and tracking",
   "titleGenerationStatus": "success",
   "createdAt": 1776871296744,
-  "updatedAt": 1777005991920,
-  "lastResponseAt": 1777005991920,
+  "updatedAt": 1777007031552,
+  "lastResponseAt": 1777007031552,
   "sessionId": "50e1c568-9493-4c86-8ca1-1f50b0f2e724",
   "providerState": {
     "providerSessionId": "50e1c568-9493-4c86-8ca1-1f50b0f2e724"
@@ -15,12 +15,12 @@
   ],
   "usage": {
     "model": "kimi-for-coding",
-    "inputTokens": 86018,
+    "inputTokens": 88635,
     "cacheCreationInputTokens": 0,
     "cacheReadInputTokens": 0,
     "contextWindow": 200000,
-    "contextTokens": 86018,
-    "percentage": 43,
+    "contextTokens": 88635,
+    "percentage": 44,
     "contextWindowIsAuthoritative": true
   }
 }
\ No newline at end of file
diff --git a/自动语义分割系统/ComfyUI 搭建操作指南.md b/自动语义分割系统/ComfyUI 搭建操作指南.md
index 7d9f9d8..bd92387 100644
--- a/自动语义分割系统/ComfyUI 搭建操作指南.md	
+++ b/自动语义分割系统/ComfyUI 搭建操作指南.md	
@@ -172,6 +172,17 @@ tags:
 3. 参数调整（可选）：
    - `points_per_side`: 网格密度（默认 32，越大越精细但越慢）
    - `pred_iou_thresh`: IOU 阈值过滤低质量 mask
+   - `stability_score_thresh`: 稳定性阈值（默认 0.95）
+
+**医疗/低对比度场景调优建议**
+
+在处理医疗手术图像等低对比度、边界模糊场景时，Auto Segmentation 容易因过滤过严而产生"角落碎块"（只保留高对比度杂色，漏掉目标器官）。遇到此现象时请重点调整以下两个参数：
+
+| 参数 | 当前问题 | 建议修改 |
+|:---|:---|:---|
+| `stability_score_thresh` | 默认 0.95 要求过高。手术灯光反光、组织颜色接近，AI 很难在全图点阵下获得 95% 稳定性的遮罩，导致宁缺毋滥、滤掉模糊器官 | **降至 0.85 ~ 0.90** |
+| `points_per_side` | 默认 16 意味着全图只撒了 256 个探测点。对于 2560×1440 等高分辨率医疗画面，点阵空隙太大，容易漏掉细小器械或解剖结构 | **提高至 32 或 64** |
+
 4. 输出：`mask`、`segmented_image`、`bbox`
 
 **此时你可以先点击「运行」测试单帧分割效果。**