Skip to content

Commit

Permalink
Browse files Browse the repository at this point in the history
  • Loading branch information
ryogrid committed Oct 14, 2024
2 parents e59d2a4 + c46d3d7 commit 836e5b6
Showing 1 changed file with 8 additions and 8 deletions.
16 changes: 8 additions & 8 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,15 +1,15 @@
# Anime Style Illustration Specific Image Search App with Vit Tagger x LSI
# Anime Style Illustration Specific Image Search App with ViT Tagger x LSI
## What's This?
- Anime Style Illustration Specific Image Search App with ML Technique
- can be used for photos. but flexible photo search is offered by Google Photos or etc :)
- Search capabilities of cloud photo album services towards illustration image files are poor for some reason
- So, I wrote simple scripts

## Method
- Search Images matching with Query Texts on Latent Representation Vectors
- Search Images Matching with Query Texts on Latent Semantic Representation Vector Space
- Vectors are generated with embedding model: Visual Transformar (ViT) Tagger x Latent Semantic Indexing (LSI)
- LSI is Ssed for Covering Tagging Presision
- You can use tags to search which are difficult for tagging because search index is applyed LSI
- LSI is used for Covering Tagging Presision
- You can use tags to search which are difficult for tagging because the index data which is composed of vectors is applyed LSI
- implemented with Gensim lib
- ( Web UI is implemented with StreamLit )

Expand All @@ -18,7 +18,7 @@
- $ python make-tags-with-wd-tagger.py --dir "IMAGE FILES CONTAINED DIR PATH"
- The script searches directory structure recursively :)
- This takes quite a while...
- About 1 file/s at middle spec desktop PC (GPU is not used)
- About 0.5 sec/file at middle spec desktop PC (GPU is not used)
- AMD Ryzen 7 5700X 8-Core Processor 4.50 GHz
- You may speed up with editing the script to use CUDAExecutionProvider, CoreMLExecutionProvider and etc :)
- Plese see [here](https://onnxruntime.ai/docs/execution-providers/)
Expand All @@ -43,7 +43,7 @@
- Solution
- Search words you want to use from taggs-wd-tagger.txt with grep, editor or something for existance checking
- If exist, there is no problem. If not, you should think similar words and search it in same manner :)
- Charcter code of file pathes
- Character code of file pathes
- If file path contains charactors which can't be contered to Unicode or utf-8, scripts may ouput error message at processing the file
- But, it doesn't mean that your script usage is wrong. Though these files is ignored or not displayed at Web UI :|
- This is problem of current implentation. When you use scripts on Windows and charactor code of directory/file names isn't utf-8, the problem may occur
Expand All @@ -55,11 +55,11 @@

## TODO
- [ ] <del>Search on latent representation generated by CLIP model</del>
- This was tried but precition with current public available CLIP models which are not fit for anime style illust was bad :|
- This was alredy tried but precition was not good because current public available CLIP models are not fitting for anime style illust :|
- [ ] Weight specifying to keyword like prompt format of Stable Diffusion Web UI
- Current implemenataion uses all keywords faialy. But there is many cases that users want to emphasize specific keyword and can't get appropriate results without that!
- [ ] Incremental index updating at image files increasing
- [ ] Similar image search with specifying target image file
- [ ] Similar image search with specifying a image file
- [ ] Exporting found files list feature
- In text file. Once you get list, many other tools and viewer you like can be used :)
- [ ] Making binary package of this app which doesn't need python environment building
Expand Down

0 comments on commit 836e5b6

Please sign in to comment.