mirrors/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-09-10 19:46:38 +00:00
Code Issues Packages Projects Releases Wiki Activity

Make --novram completely offload weights.

Browse Source 
This flag is mainly used for testing the weight offloading, it shouldn't
actually be used in practice.

Remove useless import.
This commit is contained in:
comfyanonymous
2024-12-23 01:50:11 -05:00
parent 56bc64f351
commit e44d0ac7f7
2 changed files with 1 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
comfy/model_management.py
View File

@@ -521,7 +521,7 @@ def load_models_gpu(models, memory_required=0, force_patch_weights=False, minimu
lowvram_model_memory = 0
if vram_set_state == VRAMState.NO_VRAM:
lowvram_model_memory = 64 * 1024 * 1024
lowvram_model_memory = 0.1
loaded_model.model_load(lowvram_model_memory, force_patch_weights=force_patch_weights)
current_loaded_models.insert(0, loaded_model)