Super-squash branch 'main' using huggingface_hub

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Danbooru Tag to Japanese Tag Converter V2
+emoji: 📦😻
+colorFrom: pink
+colorTo: yellow
+sdk: gradio
+sdk_version: 4.38.1
+app_file: app.py
+pinned: false
+license: apache-2.0
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,33 @@
+import gradio as gr
+from danbooru_to_ja import danbooru_to_ja
+
+DESCRIPTION_MD = """
+# Convert Danbooru tags to Japanese tags V2
+- [A CLI version of this tool is available here](https://huggingface.co/spaces/John6666/danbooru-to-ja-v2/tree/main/local).
+""".strip()
+
+DESCRIPTION_MD2 = """
+The dictionary was generated using the following repository:\
+      [p1atdev/danbooru-ja-tag-pair-20240715](https://huggingface.co/datasets/p1atdev/danbooru-ja-tag-pair-20240715)
+""".strip()
+
+css = """"""
+
+with gr.Blocks(theme="NoCrypt/miku@>=1.2.2", css=css) as demo:
+    gr.Markdown(DESCRIPTION_MD)
+    with gr.Column(): 
+        input_tag = gr.Textbox(label="Input tag", placeholder="1girl, solo, sitting, ...", value="", lines=4)
+        is_append = gr.Checkbox(label="Append input tag to output", value=True)
+        run_button = gr.Button(value="Convert")
+        output_tag = gr.Textbox(label="Output tag", value="", lines=4, interactive=False, show_copy_button=True)
+    gr.Markdown(DESCRIPTION_MD2)
+
+    gr.on(
+        triggers=[input_tag.submit, run_button.click],
+        fn=danbooru_to_ja,
+        inputs=[input_tag, gr.Textbox(visible=False), gr.Textbox(visible=False), is_append],
+        outputs=[output_tag],
+    )
+
+demo.queue()
+demo.launch()

danbooru_to_ja.py

@@ -0,0 +1,78 @@
+import argparse
+import re
+from pathlib import Path
+
+
+def load_json_dict(path: str):
+    import json
+    from pathlib import Path
+    dict = {}
+    if not Path(path).exists(): return dict
+    try:
+        with open(path, encoding='utf-8') as f:
+            dict = json.load(f)
+    except Exception:
+        print(f"Failed to open dictionary file: {path}")
+        return dict
+    return dict
+
+
+danbooru_ja_dict = load_json_dict('danbooru_ja_dict.json')
+
+
+def danbooru_tags_to_jas(tags: list[str]):
+    from rapidfuzz.process import extractOne
+    from rapidfuzz.utils import default_process
+    A1111_SPECIAL_SYNTAX_RE = re.compile(r"\s*<[^>]+>\s*")
+    keys = list(danbooru_ja_dict.keys())
+    jas = []
+    for tag in tags:
+        tag = str(tag).strip()
+        if A1111_SPECIAL_SYNTAX_RE.fullmatch(tag): continue
+        s = default_process(str(tag))
+        e1 = extractOne(s, keys, processor=default_process, score_cutoff=90.0)
+        if e1:
+            jas.extend(danbooru_ja_dict[e1[0]].copy())
+    return jas
+
+
+def danbooru_to_ja(input_tag, input_file, output_file, is_append):
+    if input_file and Path(input_file).exists():
+        try:
+            with open(input_file, 'r', encoding='utf-8') as f:
+                input_tag = f.read()
+        except Exception:
+            print(f"Failed to open input file: {input_file}")
+    tags = [tag.strip() for tag in input_tag.split(",")] if input_tag else []
+    ja_tags = danbooru_tags_to_jas(tags)
+    output_tags = tags + ja_tags if is_append else ja_tags
+    output_tag = ", ".join(output_tags)
+    if output_file:
+        try:
+            with open(output_file, mode='w', encoding="utf-8") as f:
+                f.write(output_tag)
+        except Exception:
+            print(f"Failed to write output file: {output_file}")
+    else:
+        print(output_tag)
+    return output_tag
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--tags", default=None, type=str, required=False, help="Input tags.")
+    parser.add_argument("--file", default=None, type=str, required=False, help="Input tags from a text file.")
+    parser.add_argument("--out", default=None, type=str, help="Output to text file.")
+    parser.add_argument("--append", default=False, type=bool, help="Whether the output contains the input tags or not.")
+
+    args = parser.parse_args()
+    assert (args.tags, args.file) != (None, None), "Must provide --tags or --file!"
+
+    danbooru_to_ja(args.tags, args.file, args.out, args.append)
+
+
+# Usage:
+# python danbooru_to_ja.py --tags "1girl, oomuro sakurako, solo, sitting, starry sky"
+# python danbooru_to_ja.py --file inputtag.txt
+# python danbooru_to_ja.py --file inputtag.txt --append True
+# Datasets: https://huggingface.co/datasets/p1atdev/danbooru-ja-tag-pair-20240715

local/danbooru_to_ja.py

@@ -0,0 +1,78 @@
+import argparse
+import re
+from pathlib import Path
+
+
+def load_json_dict(path: str):
+    import json
+    from pathlib import Path
+    dict = {}
+    if not Path(path).exists(): return dict
+    try:
+        with open(path, encoding='utf-8') as f:
+            dict = json.load(f)
+    except Exception:
+        print(f"Failed to open dictionary file: {path}")
+        return dict
+    return dict
+
+
+danbooru_ja_dict = load_json_dict('danbooru_ja_dict.json')
+
+
+def danbooru_tags_to_jas(tags: list[str]):
+    from rapidfuzz.process import extractOne
+    from rapidfuzz.utils import default_process
+    A1111_SPECIAL_SYNTAX_RE = re.compile(r"\s*<[^>]+>\s*")
+    keys = list(danbooru_ja_dict.keys())
+    jas = []
+    for tag in tags:
+        tag = str(tag).strip()
+        if A1111_SPECIAL_SYNTAX_RE.fullmatch(tag): continue
+        s = default_process(str(tag))
+        e1 = extractOne(s, keys, processor=default_process, score_cutoff=90.0)
+        if e1:
+            jas.extend(danbooru_ja_dict[e1[0]].copy())
+    return jas
+
+
+def danbooru_to_ja(input_tag, input_file, output_file, is_append):
+    if input_file and Path(input_file).exists():
+        try:
+            with open(input_file, 'r', encoding='utf-8') as f:
+                input_tag = f.read()
+        except Exception:
+            print(f"Failed to open input file: {input_file}")
+    tags = [tag.strip() for tag in input_tag.split(",")] if input_tag else []
+    ja_tags = danbooru_tags_to_jas(tags)
+    output_tags = tags + ja_tags if is_append else ja_tags
+    output_tag = ", ".join(output_tags)
+    if output_file:
+        try:
+            with open(output_file, mode='w', encoding="utf-8") as f:
+                f.write(output_tag)
+        except Exception:
+            print(f"Failed to write output file: {output_file}")
+    else:
+        print(output_tag)
+    return output_tag
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--tags", default=None, type=str, required=False, help="Input tags.")
+    parser.add_argument("--file", default=None, type=str, required=False, help="Input tags from a text file.")
+    parser.add_argument("--out", default=None, type=str, help="Output to text file.")
+    parser.add_argument("--append", default=False, type=bool, help="Whether the output contains the input tags or not.")
+
+    args = parser.parse_args()
+    assert (args.tags, args.file) != (None, None), "Must provide --tags or --file!"
+
+    danbooru_to_ja(args.tags, args.file, args.out, args.append)
+
+
+# Usage:
+# python danbooru_to_ja.py --tags "1girl, oomuro sakurako, solo, sitting, starry sky"
+# python danbooru_to_ja.py --file inputtag.txt
+# python danbooru_to_ja.py --file inputtag.txt --append True
+# Datasets: https://huggingface.co/datasets/p1atdev/danbooru-ja-tag-pair-20240715

local/requirements.txt

@@ -0,0 +1 @@
+rapidfuzz

requirements.txt

@@ -0,0 +1 @@
+rapidfuzz