Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

add a new FAQ for converting safetensors

Browse Source
This commit is contained in:
Lincoln Stein 2024-08-10 17:53:26 -04:00 committed by Kent Keirsey
parent 8ecf72838d
commit be48323a06
1 changed files with 16 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
docs/help/FAQ.md
View File

@ -197,6 +197,22 @@ tips to reduce the problem:
This should be sufficient to generate larger images up to about 1280x1280.
## Checkpoint Models Load Slowly or Use Too Much RAM
The difference between diffusers models (a folder containing multiple
subfolders) and checkpoint models (a file ending with .safetensors or
.ckpt) is that InvokeAI is able to load diffusers models into memory
incrementally, while checkpoint models must be loaded all at
once. With very large models, or systems with limited RAM, you may
experience slowdowns and other memory-related issues when loading
checkpoint models.
To solve this, go to the Model Manager tab (the cube), select the
checkpoint model that's giving you trouble, and press the "Convert"
button in the upper right of your browser window. This will conver the
checkpoint into a diffusers model, after which loading should be
faster and less memory-intensive.
## Memory Leak (Linux)
If you notice a memory leak, it could be caused to memory fragmentation as models are loaded and/or moved from CPU to GPU.