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

Merge branch 'diffusers_cross_attention_control_reimplementation' of github.com:damian0815/InvokeAI into diffusers_cross_attention_control_reimplementation

Browse Source
This commit is contained in:
Damian Stewart 2023-01-30 16:23:52 +01:00
commit 817e36f8bf
1 changed files with 18 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
docs/CHANGELOG.md
View File

@ -52,12 +52,17 @@ introduces several changes you should know about.
path: models/diffusers/hakurei-haifu-diffusion-1.4 path: models/diffusers/hakurei-haifu-diffusion-1.4
``` ```
2. The format of the models directory has changed to mimic the 2. In order of precedence, InvokeAI will now use HF_HOME, then
HuggingFace cache directory. By default, diffusers models are XDG_CACHE_HOME, then finally default to `ROOTDIR/models` to
now automatically downloaded and retrieved from the directory store HuggingFace diffusers models.
`ROOTDIR/models/diffusers`, while other models are stored in
the directory `ROOTDIR/models/hub`. This organization is the Consequently, the format of the models directory has changed to
same as that used by HuggingFace for its cache management. mimic the HuggingFace cache directory. When HF_HOME and XDG_HOME
are not set, diffusers models are now automatically downloaded
and retrieved from the directory `ROOTDIR/models/diffusers`,
while other models are stored in the directory
`ROOTDIR/models/hub`. This organization is the same as that used
by HuggingFace for its cache management.
This allows you to share diffusers and ckpt model files easily with This allows you to share diffusers and ckpt model files easily with
other machine learning applications that use the HuggingFace other machine learning applications that use the HuggingFace
@ -66,7 +71,13 @@ introduces several changes you should know about.
cache models in. To tell InvokeAI to use the standard HuggingFace cache models in. To tell InvokeAI to use the standard HuggingFace
cache directory, you would set HF_HOME like this (Linux/Mac): cache directory, you would set HF_HOME like this (Linux/Mac):
`export HF_HOME=~/.cache/hugging_face` `export HF_HOME=~/.cache/huggingface`
Both HuggingFace and InvokeAI will fall back to the XDG_CACHE_HOME
environment variable if HF_HOME is not set; this path
takes precedence over `ROOTDIR/models` to allow for the same sharing
with other machine learning applications that use HuggingFace
libraries.
3. If you upgrade to InvokeAI 2.3.* from an earlier version, there 3. If you upgrade to InvokeAI 2.3.* from an earlier version, there
will be a one-time migration from the old models directory format will be a one-time migration from the old models directory format