app.py

import gradio as gr
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,
)
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
from tagger.v2 import V2_ALL_MODELS, v2_random_prompt
from tagger.utils import (
    V2_ASPECT_RATIO_OPTIONS, V2_RATING_OPTIONS,
    V2_LENGTH_OPTIONS, V2_IDENTITY_OPTIONS,
)


max_images = 8
load_models(models)

css = """
.model_info { text-align: center; }
.output { width=112px; height=112px; !important; }
.gallery { width=100%; min_height=768px; !important; }
"""

with gr.Blocks(theme="NoCrypt/miku@>=1.2.2", fill_width=True, css=css) as demo:
    with gr.Column(): 
        with gr.Group():
            model_name = gr.Dropdown(label="Select Model", choices=list(loaded_models.keys()), value=list(loaded_models.keys())[0], allow_custom_value=True)
            model_info = gr.Markdown(value=get_model_info_md(list(loaded_models.keys())[0]), elem_classes="model_info")
        with gr.Group():
            with gr.Accordion("Prompt from Image File", open=False):
                tagger_image = gr.Image(label="Input image", type="pil", sources=["upload", "clipboard"], height=256)
                with gr.Accordion(label="Advanced options", open=False):
                    tagger_general_threshold = gr.Slider(label="Threshold", minimum=0.0, maximum=1.0, value=0.3, step=0.01, interactive=True)
                    tagger_character_threshold = gr.Slider(label="Character threshold", minimum=0.0, maximum=1.0, value=0.8, step=0.01, interactive=True)
                    tagger_tag_type = gr.Radio(label="Convert tags to", info="danbooru for common, e621 for Pony.", choices=["danbooru", "e621"], value="danbooru")
                    tagger_recom_prompt = gr.Radio(label="Insert reccomended prompt", choices=["None", "Animagine", "Pony"], value="None", interactive=True)  
                    tagger_keep_tags = gr.Radio(label="Remove tags leaving only the following", choices=["body", "dress", "all"], value="all")
                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")
            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 🎲", size="sm", scale=1)
                clear_prompt = gr.Button(value="Clear Prompt 🗑️", size="sm", scale=1)
            prompt = gr.Text(label="Prompt", lines=2, max_lines=8, placeholder="1girl, solo, ...", show_copy_button=True)
            neg_prompt = gr.Text(label="Negative Prompt", lines=1, max_lines=8, placeholder="", visible=False)
            with gr.Accordion("Advanced options", open=False):
                width = gr.Number(label="Width", info="If 0, the default value is used.", maximum=1216, step=32, value=None)
                height = gr.Number(label="Height", info="If 0, the default value is used.", maximum=1216, step=32, value=None)
                steps = gr.Number(label="Number of inference steps", info="If 0, the default value is used.", maximum=100, step=1, value=None)
                cfg = gr.Number(label="Guidance scale", info="If 0, the default value is used.", maximum=30.0, step=0.1, value=None)
            with gr.Accordion("Recommended Prompt", open=False):
                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"])
            with gr.Accordion("Prompt Transformer", open=False):
                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)
                v2_length = gr.Radio(label="Length", info="The total length of the tags.", choices=list(V2_LENGTH_OPTIONS), value="long")
                v2_identity = gr.Radio(label="Keep identity", info="How strictly to keep the identity of the character or subject. If you specify the detail of subject in the prompt, you should choose `strict`. Otherwise, choose `none` or `lax`. `none` is very creative but sometimes ignores the input prompt.", choices=list(V2_IDENTITY_OPTIONS), value="lax")                    
                v2_ban_tags = gr.Textbox(label="Ban tags", info="Tags to ban from the output.", placeholder="alternate costumen, ...", value="censored")
                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", size="sm", interactive=False)
        image_num = gr.Slider(label="Number of images", minimum=1, maximum=max_images, value=1, step=1, interactive=True, scale=1)
        with gr.Row():
            run_button = gr.Button("Generate Image", scale=6)
            random_button = gr.Button("Random Model 🎲", scale=3)
            stop_button = gr.Button('Stop', interactive=False, scale=1)
    with gr.Column(): 
        with gr.Group():
            with gr.Row():
                output = [gr.Image(label='', elem_classes="output", type="filepath", format=".png",
                          show_download_button=True, show_share_button=False, show_label=False,
                          interactive=False, min_width=80, visible=True) for _ in range(max_images)]
        with gr.Group():
            results = gr.Gallery(label="Gallery", elem_classes="gallery", interactive=False, show_download_button=True, show_share_button=False,
                                 container=True, format="png", object_fit="cover", columns=2, rows=2)
            image_files = gr.Files(label="Download", interactive=False)
            clear_results = gr.Button("Clear Gallery / Download 🗑️")
    with gr.Column(): 
        examples = gr.Examples(
            examples = [
                ["souryuu asuka langley, 1girl, neon genesis evangelion, plugsuit, pilot suit, red bodysuit, sitting, crossing legs, black eye patch, cat hat, throne, symmetrical, looking down, from bottom, looking at viewer, outdoors"],
                ["sailor moon, magical girl transformation, sparkles and ribbons, soft pastel colors, crescent moon motif, starry night sky background, shoujo manga style"],
                ["kafuu chino, 1girl, solo"],
                ["1girl"],
                ["beautiful sunset"],
            ],
            inputs=[prompt],
        )
        gr.Markdown(
            f"""This demo was created in reference to the following demos.<br>
    [Nymbo/Flood](https://huggingface.co/spaces/Nymbo/Flood), 
    [Yntec/ToyWorldXL](https://huggingface.co/spaces/Yntec/ToyWorldXL), 
    [Yntec/Diffusion80XX](https://huggingface.co/spaces/Yntec/Diffusion80XX).
                """
        )
        gr.DuplicateButton(value="Duplicate Space")
        gr.Markdown(f"Just a few edits to *model.py* are all it takes to complete your own collection.")

    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)
    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)
        gen_event = gr.on(triggers=[run_button.click, prompt.submit],
         fn=lambda i, n, m, t1, t2, n1, n2, n3, n4, l1, l2, l3, l4: infer_fn(m, t1, t2, n1, n2, n3, n4, l1, l2, l3, l4) if (i < n) else None,
         inputs=[img_i, image_num, model_name, prompt, neg_prompt, height, width, steps, cfg,
                  positive_prefix, positive_suffix, negative_prefix, negative_suffix],
         outputs=[o], queue=True, show_api=False)
        gen_event2 = gr.on(triggers=[random_button.click],
         fn=lambda i, n, m, t1, t2, n1, n2, n3, n4, l1, l2, l3, l4: infer_rand_fn(m, t1, t2, n1, n2, n3, n4, l1, l2, l3, l4) if (i < n) else None,
         inputs=[img_i, image_num, model_name, prompt, neg_prompt, height, width, steps, cfg,
                  positive_prefix, positive_suffix, negative_prefix, negative_suffix],
         outputs=[o], queue=True, show_api=False)
        o.change(save_gallery, [o, results], [results, image_files], show_api=False)
        stop_button.click(lambda: gr.update(interactive=False), None, stop_button, cancels=[gen_event, gen_event2], show_api=False)

    clear_prompt.click(lambda: None, None, [prompt], queue=False, show_api=False)
    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)

    random_prompt.click(
        v2_random_prompt, [prompt, v2_series, v2_character, v2_rating, v2_aspect_ratio, v2_length,
          v2_identity, v2_ban_tags, v2_model], [prompt, v2_series, v2_character], show_api=False,
    ).success(
        get_tag_type, [positive_prefix, positive_suffix, negative_prefix, negative_suffix], [v2_tag_type], queue=False, show_api=False
    ).success(
        convert_danbooru_to_e621_prompt, [prompt, v2_tag_type], [prompt], queue=False, show_api=False,
    )
    tagger_generate_from_image.click(
            lambda: ("", "", ""), None, [v2_series, v2_character, prompt], queue=False, show_api=False,
    ).success(
        predict_tags_wd,
        [tagger_image, prompt, tagger_algorithms, tagger_general_threshold, tagger_character_threshold],
        [v2_series, v2_character, prompt, v2_copy],
        show_api=False,
    ).success(
        predict_tags_fl2_sd3, [tagger_image, prompt, tagger_algorithms], [prompt], show_api=False,
    ).success(
        remove_specific_prompt, [prompt, tagger_keep_tags], [prompt], queue=False, show_api=False,
    ).success(
        convert_danbooru_to_e621_prompt, [prompt, tagger_tag_type], [prompt], queue=False, show_api=False,
    ).success(
        insert_recom_prompt, [prompt, neg_prompt, tagger_recom_prompt], [prompt, neg_prompt], queue=False, show_api=False,
    ).success(
        compose_prompt_to_copy, [v2_character, v2_series, prompt], [prompt], queue=False, show_api=False,
    )

demo.queue()
demo.launch()