Skip to content

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

Don't disable dynamic vram on WSL. (#15562)

comfyanonymous6b30dc206805
diff --git a/main.py b/main.py
index 361b1fc89..eb64726ea 100644
--- a/main.py
+++ b/main.py
@@ -248,7 +248,7 @@ import hook_breaker_ac10a0
import comfy.memory_management
import comfy.model_patcher
-if args.enable_dynamic_vram or (enables_dynamic_vram() and comfy.model_management.is_nvidia() and not comfy.model_management.is_wsl()):
+if args.enable_dynamic_vram or (enables_dynamic_vram() and comfy.model_management.is_nvidia()):
if (not args.enable_dynamic_vram) and (comfy.model_management.torch_version_numeric < (2, 8)):
logging.warning("Unsupported Pytorch detected. DynamicVRAM support requires Pytorch version 2.8 or later. Falling back to legacy ModelPatcher. VRAM estimates may be unreliable especially on Windows")
else: