Mirrors
/
EveryDream
mirror of https://github.com/victorchall/EveryDream.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

readme for mstevens caption gui

This commit is contained in:
Victor Hall 2022-11-21 16:19:06 -05:00
parent 51befb7c01
commit b77f0fc4d9
2 changed files with 18 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.MD
View File

@ -24,6 +24,8 @@ See clip_rename.bat for an example to chain captioning and renaming together.
[Training](https://github.com/victorchall/EveryDream-trainer) (separate repo) - Fine tuning with captioned training and ground truth data (needs 24GB GPU). [Training](https://github.com/victorchall/EveryDream-trainer) (separate repo) - Fine tuning with captioned training and ground truth data (needs 24GB GPU).
[Image Caption GUI and video frame extractors](./doc/CAPTION_GUI.md) and courtesy of [MStevenson](https://github.com/mstevenson/)
## Install ## Install
You can use conda or venv. This was developed on Python 3.10.5 but may work on older newer versions. You can use conda or venv. This was developed on Python 3.10.5 but may work on older newer versions.

16
doc/CAPTION_GUI.md Normal file
View File

@ -0,0 +1,16 @@
# MSteven's tools
## Caption GUI
python scripts/image_caption_gui.py
Python GUI tool to manually caption images for machine learning.
A sidecar file is created for each image with the same name and a .txt extension. These are compatible with EveryDream Trainer.
### Controls:
[control/command + o] to open a folder of images.
[page down] and [page up] to go to next and previous images. Hold shift to skip 10 images.
[shift + home] and [shift + end] to go to first and last images.
[shift + delete] to move the current image into a '_deleted' folder.
[escape] to exit the app.