Nodes/comfyui_yg_nodes/YG Clean VRAM
ComfyUI Node

YG Clean VRAM

A ComfyUI node in YG_Nodes with 9 inputs and 1 output.

By mallikarjunaraokoliparthi·Created 2 months ago·Updated 20 days ago· 0
YG Clean VRAM
  • passthrough
  • passthrough
unload_modelstrue
aggressivetrue
max_passes3
target_free_mb0
trigger_every_runtrue
clean_all_serversfalse
dashboard_urlhttp://127.0.0.1:8194
dashboard_token
CategoryYG_Nodes

Inputs (9)

NameTypeDefaultDescription
unload_modelsBOOLEANtrueUnload all loaded models from VRAM. Disable to keep the model cache (faster next run, more VRAM used).
aggressiveBOOLEANtrueAdds cuda.ipc_collect + synchronize after empty_cache.
max_passesINT31–10Number of clean-then-measure passes. Stops early once VRAM stops dropping.
target_free_mbINT00–200000Optional: keep cleaning until GPU 'used' drops to this many MB or below. 0 disables.
trigger_every_runBOOLEANtrueRe-execute on every workflow run (no caching).
clean_all_serversBOOLEANfalseAlso clean VRAM on ALL ComfyUI servers via the dashboard (or by POSTing /free to each port). Use this if other ComfyUI instances on the same GPU are holding memory.
dashboard_urlSTRINGhttp://127.0.0.1:8194Server Status Dashboard base URL (e.g. http://127.0.0.1:8194).
dashboard_tokenSTRINGDashboard SECRET_TOKEN.
passthroughopt*Optional value forwarded to the output.

Outputs (1)

NameTypeDescription
passthrough*