mirror of
https://github.com/comfyanonymous/ComfyUI.git
synced 2026-03-24 18:43:36 +08:00
82b868a45a
* sd: soft_empty_cache on tiler fallback This doesnt cost a lot and creates the expected VRAM reduction in resource monitors when you fallback to tiler. * wan: vae: Don't recursion in local fns (move run_up) Moved Decoder3d’s recursive run_up out of forward into a class method to avoid nested closure self-reference cycles. This avoids cyclic garbage that delays garbage of tensors which in turn delays VRAM release before tiled fallback. * ltx: vae: Don't recursion in local fns (move run_up) Mov the recursive run_up out of forward into a class method to avoid nested closure self-reference cycles. This avoids cyclic garbage that delays garbage of tensors which in turn delays VRAM release before tiled fallback. |
||
|---|---|---|
| .. | ||
| model_animate.py | ||
| model_multitalk.py | ||
| model.py | ||
| vae2_2.py | ||
| vae.py | ||