nodes/kunail0804-ComfyUI-Scene-Compiler
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix(nodes): raise analyzer node default timeout 60s -> 300s (#80)

Browse Source 
Local Ollama cold-loads the model into VRAM on the first call, so 60s often
times out (SC0013 -> no Scene) for longer prompts. Bump the ComfyUI node input
default to 300s. The library/spec default (AnalyzerConfig.timeout, MASTER_SPEC
§23.2) is left at 60 unchanged.

Co-authored-by: kunail0804 <kunail0804@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Crespin Alexandre
2026-07-10 20:10:22 +02:00
committed by GitHub
co-authored by kunail0804 Claude Opus 4.8
parent 54b76ca75a
commit 09923c161e
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
nodes/scene_analyzer_node.py
+1 -1
View File
@@ -31,7 +31,7 @@ class SceneAnalyzerNode:
"natural_language": ("STRING", {"multiline": True, "default": ""}),
"model_name": ("STRING", {"default": "llama3"}),
"temperature": ("FLOAT", {"default": 0.0, "min": 0.0, "max": 2.0, "step": 0.1}),
"timeout": ("INT", {"default": 60, "min": 1, "max": 3600}),
"timeout": ("INT", {"default": 300, "min": 1, "max": 3600}),
},
"optional": {
"system_prompt": ("STRING", {"multiline": True, "default": ""}),