mirrors/Fooocus
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix: prioritize VRAM over RAM in Colab, preventing out of memory issues (#1710)

Browse Source 
* colab: balance the use of RAM

enables the use of VRAM memory so as not to saturate the system RAM

* feat: use --always-high-vram by default for Colab, adjust readme

---------

Co-authored-by: Manuel Schmid <manuel.schmid@odt.net>
This commit is contained in:
Giuseppe Speranza 2024-03-11 19:58:25 +01:00 committed by GitHub
parent d57afc88a4
commit 532401df76
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
fooocus_colab.ipynb
View File

@ -12,7 +12,7 @@
"%cd /content\n",
"!git clone https://github.com/lllyasviel/Fooocus.git\n",
"%cd /content/Fooocus\n",
"!python entry_with_update.py --share\n"
"!python entry_with_update.py --share --always-high-vram\n"
]
}
],

6
readme.md
View File

@ -115,16 +115,18 @@ See also the common problems and troubleshoots [here](troubleshoot.md).
### Colab
(Last tested - 2023 Dec 12)
(Last tested - 2024 Mar 11)
| Colab | Info
| --- | --- |
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/lllyasviel/Fooocus/blob/main/fooocus_colab.ipynb) | Fooocus Official
In Colab, you can modify the last line to `!python entry_with_update.py --share` or `!python entry_with_update.py --preset anime --share` or `!python entry_with_update.py --preset realistic --share` for Fooocus Default/Anime/Realistic Edition.
In Colab, you can modify the last line to `!python entry_with_update.py --share --always-high-vram` or `!python entry_with_update.py --share --always-high-vram --preset anime` or `!python entry_with_update.py --share --always-high-vram --preset realistic` for Fooocus Default/Anime/Realistic Edition.
Note that this Colab will disable refiner by default because Colab free's resources are relatively limited (and some "big" features like image prompt may cause free-tier Colab to disconnect). We make sure that basic text-to-image is always working on free-tier Colab.
Using `--always-high-vram` shifts resource allocation from RAM to VRAM and achieves the overall best balance between performance, flexibility and stability on the default T4 instance.
Thanks to [camenduru](https://github.com/camenduru)!
### Linux (Using Anaconda)