wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-06-26 09:49:26 +08:00
Code Issues Actions 29 Packages Projects Releases Wiki Activity

Merge branch 'master' into feat/api-nodes/bria-replace-background

Browse Source
This commit is contained in:
Alexis Rolland 2026-06-11 12:30:14 +08:00 committed by GitHub
commit fc78f43df6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 11 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
README.md
View File

@ -462,16 +462,6 @@ To use the most up-to-date frontend version:
This approach allows you to easily switch between the stable fortnightly release and the cutting-edge daily updates, or even specific versions for testing purposes. This approach allows you to easily switch between the stable fortnightly release and the cutting-edge daily updates, or even specific versions for testing purposes.
### Accessing the Legacy Frontend
If you need to use the legacy frontend for any reason, you can access it using the following command line argument:
```
--front-end-version Comfy-Org/ComfyUI_legacy_frontend@latest
```
This will use a snapshot of the legacy frontend preserved in the [ComfyUI Legacy Frontend repository](https://github.com/Comfy-Org/ComfyUI_legacy_frontend).
# QA # QA
### Which GPU should I buy for this? ### Which GPU should I buy for this?

4
comfy/ops.py
View File

@ -299,14 +299,13 @@ def cast_bias_weight(s, input=None, dtype=None, device=None, bias_dtype=None, of
non_blocking = comfy.model_management.device_supports_non_blocking(device) non_blocking = comfy.model_management.device_supports_non_blocking(device)
if hasattr(s, "_v"): if hasattr(s, "_v") and comfy.model_management.is_device_cpu(device):
#vbar doesn't support CPU weights, but some custom nodes have weird paths #vbar doesn't support CPU weights, but some custom nodes have weird paths
#that might switch the layer to the CPU and expect it to work. We have to take #that might switch the layer to the CPU and expect it to work. We have to take
#a clone conservatively as we are mmapped and some SFT files are packed misaligned #a clone conservatively as we are mmapped and some SFT files are packed misaligned
#If you are a custom node author reading this, please move your layer to the GPU #If you are a custom node author reading this, please move your layer to the GPU
#or declare your ModelPatcher as CPU in the first place. #or declare your ModelPatcher as CPU in the first place.
if comfy.model_management.is_device_cpu(device):
materialize_meta_param(s, ["weight", "bias"]) materialize_meta_param(s, ["weight", "bias"])
weight = s.weight.to(dtype=dtype, copy=True) weight = s.weight.to(dtype=dtype, copy=True)
if isinstance(weight, QuantizedTensor): if isinstance(weight, QuantizedTensor):
@ -314,6 +313,7 @@ def cast_bias_weight(s, input=None, dtype=None, device=None, bias_dtype=None, of
bias = s.bias.to(dtype=bias_dtype, copy=True) if s.bias is not None else None bias = s.bias.to(dtype=bias_dtype, copy=True) if s.bias is not None else None
return format_return((weight, bias, (None, None, None)), offloadable) return format_return((weight, bias, (None, None, None)), offloadable)
elif hasattr(s, "_v") and s.weight.device != device:
prefetched = hasattr(s, "_prefetch") prefetched = hasattr(s, "_prefetch")
offload_stream = None offload_stream = None
offload_device = None offload_device = None

3
openapi.yaml
View File

@ -1067,6 +1067,9 @@ components:
comfyui_version: comfyui_version:
description: ComfyUI version description: ComfyUI version
type: string type: string
deploy_environment:
description: How this ComfyUI instance is deployed (e.g. cloud, local-git, local-portable, local-desktop)
type: string
embedded_python: embedded_python:
description: Whether using embedded Python description: Whether using embedded Python
type: boolean type: boolean