comfy_free_vram
Unload models and free cached memory to release VRAM, preventing out-of-memory errors in ComfyUI workflows.
Instructions
Unload models and/or free VRAM memory.
Args: unload_models: Unload all loaded models from VRAM free_memory: Free cached memory allocations
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "comfy_free_vram"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| free_memory | No | ||
| unload_models | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |