clear_vram
Free GPU VRAM by unloading cached ComfyUI models. Use between runs when switching model families or low on VRAM. Optionally unload only models or only memory.
Instructions
Free GPU VRAM by unloading cached models from ComfyUI. Use this between generation runs with different model families (e.g. switching from SDXL to Flux) or when running low on VRAM. Optionally unload only models or only memory.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| unload_models | No | Unload all cached models (default: true) | |
| free_memory | No | Free cached memory/intermediates (default: true) |