nodes/GiusTex-ComfyUI-DiffusersImageOutpaint
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
GiusTex
2024-10-21 08:44:23 +02:00
committed by GitHub
parent f023ed445f
commit 01af57ba4e
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -3,7 +3,7 @@ ComfyUI nodes for outpainting images with diffusers, based on [diffusers-image-o
![DiffusersImageOutpaint-Nodes-Screen](https://github.com/user-attachments/assets/2722e07c-1d6a-416e-a9d8-f26aaa9a45a7)
#### Updates:
- You can test the updates in the `Test` branch not yet merged opening a terminal in the extension folder, and typing `git checkout`, then `git pull`.
- You can test the updates in the `Test` branch not yet merged opening a terminal in the extension folder, and typing `git checkout Test`, then `git pull`.
- You don't need any more the diffusers vae, and can use the extension in low vram mode using `sequential_cpu_offload` (also thanks to [zmwv823](https://github.com/GiusTex/ComfyUI-DiffusersImageOutpaint/pull/4)) that pushes the vram usage from *8,3 gb* down to **_6 gb_**.
- If your `text_encoder` and `text_encoder_2` names contain `.fp16.` or other things before `safetensors`, you need to remove it (see the table below).