Upload 11 files

app.py

@@ -3,7 +3,7 @@ from model import models
 from multit2i import (load_models, infer_fn, infer_rand_fn, save_gallery,
     change_model, warm_model, get_model_info_md, loaded_models,
     get_positive_prefix, get_positive_suffix, get_negative_prefix, get_negative_suffix,
-    get_recom_prompt_type, set_recom_prompt_preset, get_tag_type)
+    get_recom_prompt_type, set_recom_prompt_preset, get_tag_type, randomize_seed, translate_to_en)
 from tagger.tagger import (predict_tags_wd, remove_specific_prompt, convert_danbooru_to_e621_prompt,
     insert_recom_prompt, compose_prompt_to_copy)
 from tagger.fl2sd3longcap import predict_tags_fl2_sd3
@@ -38,6 +38,9 @@ with gr.Blocks(theme="NoCrypt/miku@>=1.2.2", fill_width=True, css=css) as demo:
                     tagger_algorithms = gr.CheckboxGroup(["Use WD Tagger", "Use Florence-2-SD3-Long-Captioner"], label="Algorithms", value=["Use WD Tagger"])
                     tagger_generate_from_image = gr.Button(value="Generate Tags from Image", variant="secondary")
                 with gr.Accordion("Prompt Transformer", open=False):
+                    with gr.Row():
+                        v2_character = gr.Textbox(label="Character", placeholder="hatsune miku", scale=2)
+                        v2_series = gr.Textbox(label="Series", placeholder="vocaloid", scale=2)
                     with gr.Row():
                         v2_rating = gr.Radio(label="Rating", choices=list(V2_RATING_OPTIONS), value="sfw")
                         v2_aspect_ratio = gr.Radio(label="Aspect ratio", info="The aspect ratio of the image.", choices=list(V2_ASPECT_RATIO_OPTIONS), value="square", visible=False)
@@ -48,29 +51,29 @@ with gr.Blocks(theme="NoCrypt/miku@>=1.2.2", fill_width=True, css=css) as demo:
                         v2_tag_type = gr.Radio(label="Tag Type", info="danbooru for common, e621 for Pony.", choices=["danbooru", "e621"], value="danbooru", visible=False)
                     v2_model = gr.Dropdown(label="Model", choices=list(V2_ALL_MODELS.keys()), value=list(V2_ALL_MODELS.keys())[0])
                     v2_copy = gr.Button(value="Copy to clipboard", variant="secondary", size="sm", interactive=False)
-                with gr.Row():
-                    v2_character = gr.Textbox(label="Character", placeholder="hatsune miku", scale=2)
-                    v2_series = gr.Textbox(label="Series", placeholder="vocaloid", scale=2)
-                    random_prompt = gr.Button(value="Extend Prompt 🎲", variant="secondary", size="sm", scale=1)
-                    clear_prompt = gr.Button(value="Clear Prompt 🗑️", variant="secondary", size="sm", scale=1)
+                    random_prompt = gr.Button(value="Extend 🎲", variant="secondary")
                 prompt = gr.Text(label="Prompt", lines=2, max_lines=8, placeholder="1girl, solo, ...", show_copy_button=True)
                 with gr.Accordion("Advanced options", open=False):
                     neg_prompt = gr.Text(label="Negative Prompt", lines=1, max_lines=8, placeholder="")
                     with gr.Row():
                         width = gr.Slider(label="Width", info="If 0, the default value is used.", maximum=1216, step=32, value=0)
                         height = gr.Slider(label="Height", info="If 0, the default value is used.", maximum=1216, step=32, value=0)
-                    with gr.Row():
                         steps = gr.Slider(label="Number of inference steps", info="If 0, the default value is used.", maximum=100, step=1, value=0)
+                    with gr.Row():
                         cfg = gr.Slider(label="Guidance scale", info="If 0, the default value is used.", maximum=30.0, step=0.1, value=0)
                         seed = gr.Slider(label="Seed", info="Randomize Seed if -1.", minimum=-1, maximum=MAX_SEED, step=1, value=-1)
+                        seed_rand = gr.Button("Randomize Seed 🎲", size="sm", variant="secondary")
                     recom_prompt_preset = gr.Radio(label="Set Presets", choices=get_recom_prompt_type(), value="Common")
                     with gr.Row():
                         positive_prefix = gr.CheckboxGroup(label="Use Positive Prefix", choices=get_positive_prefix(), value=[])
                         positive_suffix = gr.CheckboxGroup(label="Use Positive Suffix", choices=get_positive_suffix(), value=["Common"])
                         negative_prefix = gr.CheckboxGroup(label="Use Negative Prefix", choices=get_negative_prefix(), value=[])
                         negative_suffix = gr.CheckboxGroup(label="Use Negative Suffix", choices=get_negative_suffix(), value=["Common"])
-
-                image_num = gr.Slider(label="Number of images", minimum=1, maximum=max_images, value=1, step=1, interactive=True, scale=1)
+                with gr.Row():
+                    image_num = gr.Slider(label="Number of images", minimum=1, maximum=max_images, value=1, step=1, interactive=True, scale=2)
+                    trans_prompt = gr.Button(value="Translate 📝", variant="secondary", size="sm", scale=2)
+                    clear_prompt = gr.Button(value="Clear 🗑️", variant="secondary", size="sm", scale=1)
+                
             with gr.Row():
                 run_button = gr.Button("Generate Image", variant="primary", scale=6)
                 random_button = gr.Button("Random Model 🎲", variant="secondary", scale=3)
@@ -112,7 +115,7 @@ with gr.Blocks(theme="NoCrypt/miku@>=1.2.2", fill_width=True, css=css) as demo:
 
     #gr.on(triggers=[run_button.click, prompt.submit, random_button.click], fn=lambda: gr.update(interactive=True), inputs=None, outputs=stop_button, show_api=False)
     model_name.change(change_model, [model_name], [model_info], queue=False, show_api=False)\
-    .success(warm_model, [model_name], None, queue=True, show_api=False)
+    .success(warm_model, [model_name], None, queue=False, show_api=False)
     for i, o in enumerate(output):
         img_i = gr.Number(i, visible=False)
         image_num.change(lambda i, n: gr.update(visible = (i < n)), [img_i, image_num], o, show_api=False)
@@ -133,6 +136,9 @@ with gr.Blocks(theme="NoCrypt/miku@>=1.2.2", fill_width=True, css=css) as demo:
     clear_results.click(lambda: (None, None), None, [results, image_files], queue=False, show_api=False)
     recom_prompt_preset.change(set_recom_prompt_preset, [recom_prompt_preset],
      [positive_prefix, positive_suffix, negative_prefix, negative_suffix], queue=False, show_api=False)
+    seed_rand.click(randomize_seed, None, [seed], queue=False, show_api=False)
+    trans_prompt.click(translate_to_en, [prompt], [prompt], queue=False, show_api=False)\
+    .then(translate_to_en, [neg_prompt], [neg_prompt], queue=False, show_api=False)
 
     random_prompt.click(
         v2_random_prompt, [prompt, v2_series, v2_character, v2_rating, v2_aspect_ratio, v2_length,

multit2i.py

@@ -60,7 +60,7 @@ def find_model_list(author: str="", tags: list[str]=[], not_tag="", sort: str="l
     limit = limit * 20 if check_status and force_gpu else limit * 5
     models = []
     try:
-        model_infos = api.list_models(author=author, task="text-to-image",
+        model_infos = api.list_models(author=author, #task="text-to-image",
                                        tags=list_uniq(default_tags + tags), cardData=True, sort=sort, limit=limit)
     except Exception as e:
         print(f"Error: Failed to list models.")
@@ -110,7 +110,7 @@ def get_t2i_model_info_dict(repo_id: str):
 
 
 def rename_image(image_path: str | None, model_name: str, save_path: str | None = None):
-    from PIL import Image
+    import shutil
     from datetime import datetime, timezone, timedelta
     if image_path is None: return None
     dt_now = datetime.now(timezone(timedelta(hours=9)))
@@ -118,7 +118,7 @@ def rename_image(image_path: str | None, model_name: str, save_path: str | None
     try:
         if Path(image_path).exists():
             png_path = "image.png"
-            Image.open(image_path).convert('RGBA').save(png_path, "PNG")
+            if str(Path(image_path).resolve()) != str(Path(png_path).resolve()): shutil.copy(image_path, png_path)
             if save_path is not None:
                 new_path = str(Path(png_path).resolve().rename(Path(save_path).resolve()))
             else:
@@ -363,16 +363,16 @@ def warm_model(model_name: str):
 
 # https://huggingface.co/docs/api-inference/detailed_parameters
 # https://huggingface.co/docs/huggingface_hub/package_reference/inference_client
-def infer_body(client: InferenceClient | gr.Interface | object, prompt: str, neg_prompt: str | None = None,
-               height: int | None = None, width: int | None = None,
-               steps: int | None = None, cfg: int | None = None, seed: int = -1):
+def infer_body(client: InferenceClient | gr.Interface | object, model_str: str, prompt: str, neg_prompt: str = "",
+               height: int = 0, width: int = 0, steps: int = 0, cfg: int = 0, seed: int = -1):
     png_path = "image.png"
     kwargs = {}
-    if height is not None and height >= 256: kwargs["height"] = height
-    if width is not None and width >= 256: kwargs["width"] = width
-    if steps is not None and steps >= 1: kwargs["num_inference_steps"] = steps
-    if cfg is not None and cfg > 0: cfg = kwargs["guidance_scale"] = cfg
-    if seed >= 0: kwargs["seed"] = seed
+    if height > 0: kwargs["height"] = height
+    if width > 0: kwargs["width"] = width
+    if steps > 0: kwargs["num_inference_steps"] = steps
+    if cfg > 0: cfg = kwargs["guidance_scale"] = cfg
+    if seed == -1: kwargs["seed"] = randomize_seed()
+    else: kwargs["seed"] = seed
     try:
         if isinstance(client, InferenceClient):
             image = client.text_to_image(prompt=prompt, negative_prompt=neg_prompt, **kwargs, token=HF_TOKEN)
@@ -380,26 +380,18 @@ def infer_body(client: InferenceClient | gr.Interface | object, prompt: str, neg
             image = client.fn(prompt=prompt, negative_prompt=neg_prompt, **kwargs, token=HF_TOKEN)
         else: return None
         if isinstance(image, tuple): return None
-        image.save(png_path)
-        return str(Path(png_path).resolve())
+        return save_image(image, png_path, model_str, prompt, neg_prompt, height, width, steps, cfg, seed)
     except Exception as e:
         print(e)
         raise Exception() from e
 
 
-async def infer(model_name: str, prompt: str, neg_prompt: str | None = None,
-               height: int | None = None, width: int | None = None,
-               steps: int | None = None, cfg: int | None = None, seed: int = -1,
+async def infer(model_name: str, prompt: str, neg_prompt: str ="", height: int = 0, width: int = 0,
+               steps: int = 0, cfg: int = 0, seed: int = -1,
                save_path: str | None = None, timeout: float = inference_timeout):
-    import random
-    noise = ""
-    if seed < 0:
-        rand = random.randint(1, 500)
-        for i in range(rand):
-            noise += " "
     model = load_model(model_name)
     if not model: return None
-    task = asyncio.create_task(asyncio.to_thread(infer_body, model, f"{prompt} {noise}", neg_prompt,
+    task = asyncio.create_task(asyncio.to_thread(infer_body, model, model_name, prompt, neg_prompt,
                                                  height, width, steps, cfg, seed))
     await asyncio.sleep(0)
     try:
@@ -423,8 +415,8 @@ async def infer(model_name: str, prompt: str, neg_prompt: str | None = None,
 
 
 # https://github.com/aio-libs/pytest-aiohttp/issues/8 # also AsyncInferenceClient is buggy.
-def infer_fn(model_name: str, prompt: str, neg_prompt: str | None = None, height: int | None = None,
-             width: int | None = None, steps: int | None = None, cfg: int | None = None, seed: int = -1,
+def infer_fn(model_name: str, prompt: str, neg_prompt: str = "", height: int = 0, width: int = 0,
+             steps: int = 0, cfg: int = 0, seed: int = -1,
              pos_pre: list = [], pos_suf: list = [], neg_pre: list = [], neg_suf: list = [], save_path: str | None = None):
     if model_name == 'NA':
         return None
@@ -446,8 +438,8 @@ def infer_fn(model_name: str, prompt: str, neg_prompt: str | None = None, height
     return result
 
 
-def infer_rand_fn(model_name_dummy: str, prompt: str, neg_prompt: str | None = None, height: int | None = None,
-             width: int | None = None, steps: int | None = None, cfg: int | None = None, seed: int = -1,
+def infer_rand_fn(model_name_dummy: str, prompt: str, neg_prompt: str = "", height: int = 0, width: int = 0,
+             steps: int = 0, cfg: int = 0, seed: int = -1,
              pos_pre: list = [], pos_suf: list = [], neg_pre: list = [], neg_suf: list = [], save_path: str | None = None):
     import random
     if model_name_dummy == 'NA':
@@ -470,3 +462,41 @@ def infer_rand_fn(model_name_dummy: str, prompt: str, neg_prompt: str | None = N
     finally:
         loop.close()
     return result
+
+
+def save_image(image, savefile, modelname, prompt, nprompt, height=0, width=0, steps=0, cfg=0, seed=-1):
+    from PIL import Image, PngImagePlugin
+    import json
+    try:
+        metadata = {"prompt": prompt, "negative_prompt": nprompt, "Model": {"Model": modelname.split("/")[-1]}}
+        if steps > 0: metadata["num_inference_steps"] = steps
+        if cfg > 0: metadata["guidance_scale"] = cfg
+        if seed != -1: metadata["seed"] = seed
+        if width > 0 and height > 0: metadata["resolution"] = f"{width} x {height}"
+        metadata_str = json.dumps(metadata)
+        info = PngImagePlugin.PngInfo()
+        info.add_text("metadata", metadata_str)
+        image.save(savefile, "PNG", pnginfo=info)
+        return str(Path(savefile).resolve())
+    except Exception as e:
+        print(f"Failed to save image file: {e}")
+        raise Exception(f"Failed to save image file:") from e
+
+
+def randomize_seed():
+    from random import seed, randint
+    MAX_SEED = 2**32-1
+    seed()
+    rseed = randint(0, MAX_SEED)
+    return rseed
+
+
+from translatepy import Translator
+translator = Translator()
+def translate_to_en(input: str):
+    try:
+        output = str(translator.translate(input, 'English'))
+    except Exception as e:
+        output = input
+        print(e)
+    return output

requirements.txt

@@ -6,7 +6,5 @@ transformers
 optimum[onnxruntime]
 spaces
 dartrs
-httpx==0.13.3
-httpcore
-googletrans==4.0.0rc1
+translatepy
 timm

tagger/tagger.py

@@ -2,10 +2,7 @@ import spaces
 from PIL import Image
 import torch
 import gradio as gr
-from transformers import (
-    AutoImageProcessor,
-    AutoModelForImageClassification,
-)
+from transformers import AutoImageProcessor, AutoModelForImageClassification
 from pathlib import Path
 
 
@@ -190,18 +187,16 @@ def convert_danbooru_to_e621_prompt(input_prompt: str = "", prompt_type: str = "
     return output_prompt
 
 
-def translate_prompt(prompt: str = ""):
-    def translate_to_english(prompt):
-        import httpcore
-        setattr(httpcore, 'SyncHTTPTransport', 'AsyncHTTPProxy')
-        from googletrans import Translator
-        translator = Translator()
+from translatepy import Translator
+translator = Translator()
+def translate_prompt_old(prompt: str = ""):
+    def translate_to_english(input: str):
         try:
-            translated_prompt = translator.translate(prompt, src='auto', dest='en').text
-            return translated_prompt
+            output = str(translator.translate(input, 'English'))
         except Exception as e:
+            output = input
             print(e)
-            return prompt
+        return output
 
     def is_japanese(s):
         import unicodedata
@@ -223,18 +218,23 @@ def translate_prompt(prompt: str = ""):
     return ", ".join(outputs)
 
 
+def translate_prompt(input: str):
+    try:
+        output = str(translator.translate(input, 'English'))
+    except Exception as e:
+        output = input
+        print(e)
+    return output
+
+
 def translate_prompt_to_ja(prompt: str = ""):
-    def translate_to_japanese(prompt):
-        import httpcore
-        setattr(httpcore, 'SyncHTTPTransport', 'AsyncHTTPProxy')
-        from googletrans import Translator
-        translator = Translator()
+    def translate_to_japanese(input: str):
         try:
-            translated_prompt = translator.translate(prompt, src='en', dest='ja').text
-            return translated_prompt
+            output = str(translator.translate(input, 'Japanese'))
         except Exception as e:
+            output = input
             print(e)
-            return prompt
+        return output
 
     def is_japanese(s):
         import unicodedata