wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-01-26 06:10:15 +08:00
Code Issues Actions 17 Packages Projects Releases Wiki Activity

macOS latest with fp16 enabled by default

Browse Source
This commit is contained in:
Benjamin Berman 2023-08-01 12:59:18 -07:00
parent ab245b5c0c
commit 7c197409be
3 changed files with 6 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
README.md
View File

@ -102,13 +102,13 @@ To run it on colab or paperspace you can use my [Colab Notebook](notebooks/comfy
``` ```
2. Activate it: 2. Activate it:
**Windows:** **Windows (PowerShell):**
```pwsh ```pwsh
Set-ExecutionPolicy Unrestricted -Scope Process Set-ExecutionPolicy Unrestricted -Scope Process
& .\venv\Scripts\activate.ps1 & .\venv\Scripts\activate.ps1
``` ```
**Linux, macOS and bash/busybox64.exe on Windows:** **Linux and macOS**
```shell ```shell
source ./venv/bin/activate source ./venv/bin/activate
``` ```
@ -130,27 +130,10 @@ To run it on colab or paperspace you can use my [Colab Notebook](notebooks/comfy
You can use `comfyui` as an API. Visit the [OpenAPI specification](comfy/api/openapi.yaml). This file can be used to generate typed clients for your preferred language. You can use `comfyui` as an API. Visit the [OpenAPI specification](comfy/api/openapi.yaml). This file can be used to generate typed clients for your preferred language.
#### Troubleshooting
If you get the "Torch not compiled with CUDA enabled" error, uninstall torch with:
```pip uninstall torch```
And install it again with the command above.
### Others: ### Others:
#### [Intel Arc](https://github.com/comfyanonymous/ComfyUI/discussions/476) #### [Intel Arc](https://github.com/comfyanonymous/ComfyUI/discussions/476)
#### Apple Mac silicon
You can install ComfyUI in Apple Mac silicon (M1 or M2) with any recent macOS version.
1. Install pytorch nightly. For instructions, read the [Accelerated PyTorch training on Mac](https://developer.apple.com/metal/pytorch/) Apple Developer guide (make sure to install the latest pytorch nightly).
1. Follow the [ComfyUI manual installation](#manual-install-windows-linux) instructions for Windows and Linux.
1. Install the ComfyUI [dependencies](#dependencies). If you have another Stable Diffusion UI [you might be able to reuse the dependencies](#i-already-have-another-ui-for-stable-diffusion-installed-do-i-really-have-to-install-all-of-these-dependencies).
1. Launch ComfyUI by running `python main.py --force-fp16`. Note that --force-fp16 will only work if you installed the latest pytorch nightly.
> **Note**: Remember to add your models, VAE, LoRAs etc. to the corresponding Comfy folders, as discussed in [ComfyUI manual installation](#manual-install-windows-linux). > **Note**: Remember to add your models, VAE, LoRAs etc. to the corresponding Comfy folders, as discussed in [ComfyUI manual installation](#manual-install-windows-linux).
#### DirectML (AMD Cards on Windows) #### DirectML (AMD Cards on Windows)

2
comfy/model_management.py
View File

@ -177,7 +177,7 @@ if args.force_fp32:
print("Forcing FP32, if this improves things please report it.") print("Forcing FP32, if this improves things please report it.")
FORCE_FP32 = True FORCE_FP32 = True
if args.force_fp16: if args.force_fp16 or cpu_state == CPUState.MPS:
print("Forcing FP16.") print("Forcing FP16.")
FORCE_FP16 = True FORCE_FP16 = True

6
requirements.txt
View File

@ -1,6 +1,6 @@
torch==2.0.0 torch
torchaudio==2.0.0 torchaudio
torchvision==0.15.1 torchvision
torchdiffeq>=0.2.3 torchdiffeq>=0.2.3
torchsde>=0.2.5 torchsde>=0.2.5
einops>=0.6.0 einops>=0.6.0