mirrors/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-05-04 21:36:14 +02:00
Code Issues Actions 24 Packages Projects Releases Wiki Activity

Lower wan memory estimation value a bit. (#9964)
Some checks failed
Python Linting / Run Ruff (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.10, [self-hosted Linux], stable) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.11, [self-hosted Linux], stable) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.12, [self-hosted Linux], stable) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.9, [self-hosted Linux], stable) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-stable (12.1, --use-pytorch-cross-attention, macos, 3.10, [self-hosted macOS], stable) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-stable (12.1, --use-pytorch-cross-attention, macos, 3.11, [self-hosted macOS], stable) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-stable (12.1, --use-pytorch-cross-attention, macos, 3.12, [self-hosted macOS], stable) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-stable (12.1, --use-pytorch-cross-attention, macos, 3.9, [self-hosted macOS], stable) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-unix-nightly (12.1, , linux, 3.11, [self-hosted Linux], nightly) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-unix-nightly (12.1, --use-pytorch-cross-attention, macos, 3.11, [self-hosted macOS], nightly) (push) Has been cancelled
Details
Execution Tests / test (macos-latest) (push) Has been cancelled
Details
Execution Tests / test (ubuntu-latest) (push) Has been cancelled
Details
Execution Tests / test (windows-latest) (push) Has been cancelled
Details
Test server launches without errors / test (push) Has been cancelled
Details
Unit Tests / test (macos-latest) (push) Has been cancelled
Details
Unit Tests / test (ubuntu-latest) (push) Has been cancelled
Details
Unit Tests / test (windows-latest) (push) Has been cancelled
Details
Close stale issues / stale (push) Has been cancelled
Details

Browse Source 
Previous pr reduced the peak memory requirement.
This commit is contained in:
comfyanonymous 2025-09-20 19:09:35 -07:00 committed by GitHub
parent 7be2b49b6b
commit d1d9eb94b1
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
comfy/supported_models.py
View File

@ -995,7 +995,7 @@ class WAN21_T2V(supported_models_base.BASE):
unet_extra_config = {}
latent_format = latent_formats.Wan21
memory_usage_factor = 1.0
memory_usage_factor = 0.9
supported_inference_dtypes = [torch.float16, torch.bfloat16, torch.float32]
@ -1004,7 +1004,7 @@ class WAN21_T2V(supported_models_base.BASE):
def __init__(self, unet_config):
super().__init__(unet_config)
self.memory_usage_factor = self.unet_config.get("dim", 2000) / 2000
self.memory_usage_factor = self.unet_config.get("dim", 2000) / 2222
def get_model(self, state_dict, prefix="", device=None):
out = model_base.WAN21(self, device=device)