dearsky/Magic123
1
0
Fork 0
Code Issues 6 Pull Requests Actions Packages Projects Releases Wiki Activity

Fix typo in readme.md

Browse Source 
defualt -> default
This commit is contained in:
Ikko Eltociear Ashimine
2023-08-05 19:17:21 +09:00
committed by GitHub
parent 4ad512ad41
commit f76465a0bf
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
readme.md
View File

@@ -72,7 +72,7 @@ python preprocess_image.py --path /path/to/image
### Step 2: Textural inversion [Optional]
Magic123 uses the defualt [textural inversion](https://huggingface.co/docs/diffusers/training/text_inversion) from diffuers, which consumes around 2.5 hours on a 32G V100. If you do not want to spend time in this textural inversion, you can: (1) study whether there is other faster textural inversion; or (2) do not use textural inversion in the loss of texture and shape consistencies. To run textural inversion:
Magic123 uses the default [textural inversion](https://huggingface.co/docs/diffusers/training/text_inversion) from diffuers, which consumes around 2.5 hours on a 32G V100. If you do not want to spend time in this textural inversion, you can: (1) study whether there is other faster textural inversion; or (2) do not use textural inversion in the loss of texture and shape consistencies. To run textural inversion:
```
bash scripts/texural_inversion/textural_inversion.sh $GPU_IDX runwayml/stable-diffusion-v1-5 /path/to/example/rgba.png /path/to/save $token_name $init_token --max_train_steps 5000