import gradio as gr from v2 import ( V2UI, parse_upsampling_output, V2_ALL_MODELS, ) from utils import ( gradio_copy_text, COPY_ACTION_JS, V2_ASPECT_RATIO_OPTIONS, V2_RATING_OPTIONS, V2_LENGTH_OPTIONS, V2_IDENTITY_OPTIONS ) from tagger import ( predict_tags_wd, convert_danbooru_to_e621_prompt, remove_specific_prompt, insert_recom_prompt, compose_prompt_to_copy, translate_prompt, sort_tags, select_random_character, ) from z3de621conv import ( predict_tags_e621, ) from fl2sd3longcap import ( predict_tags_fl2_sd3, ) from fl2basepromptgen import ( predict_tags_fl2_base_prompt_gen, ) from wdtagger import ( predict_tags_wd_large, get_wdtagger_models, SWINV2_MODEL_DSV3_REPO, CONV_MODEL_DSV3_REPO, VIT_MODEL_DSV3_REPO, VIT_LARGE_MODEL_DSV3_REPO, EVA02_LARGE_MODEL_DSV3_REPO, MOAT_MODEL_DSV2_REPO, SWIN_MODEL_DSV2_REPO, CONV_MODEL_DSV2_REPO, CONV2_MODEL_DSV2_REPO, VIT_MODEL_DSV2_REPO, ) def description_ui(): gr.Markdown( """ ## Danbooru Tags Transformer V2 Demo with WD Tagger (Image =>) Prompt => Upsampled longer prompt """ ) def description_ui2(): gr.Markdown( """ - Mod of p1atdev's [Danbooru Tags Transformer V2 Demo](https://huggingface.co/spaces/p1atdev/danbooru-tags-transformer-v2) and [WD Tagger with 🤗 transformers](https://huggingface.co/spaces/p1atdev/wd-tagger-transformers). - Models: p1atdev's [wd-swinv2-tagger-v3-hf](https://huggingface.co/p1atdev/wd-swinv2-tagger-v3-hf), [dart-v2-moe-sft](https://huggingface.co/p1atdev/dart-v2-moe-sft), [dart-v2-sft](https://huggingface.co/p1atdev/dart-v2-sft)\ , toynya's [Z3D-E621-Convnext](https://huggingface.co/toynya/Z3D-E621-Convnext), gokaygokay's [Florence-2-SD3-Captioner](https://huggingface.co/gokaygokay/Florence-2-SD3-Captioner),\ MiaoshouAI's [Florence-2-base-PromptGen](https://huggingface.co/MiaoshouAI/Florence-2-base-PromptGen),\ SmilingWolf's [wd-vit-large-tagger-v3](https://huggingface.co/SmilingWolf/wd-vit-large-tagger-v3). """ ) def main(): v2 = V2UI() with gr.Blocks() as ui: description_ui() with gr.Row(): with gr.Column(scale=2): with gr.Group(): input_image = gr.Image(label="Input image", type="pil", sources=["upload", "clipboard"], height=256) with gr.Accordion(label="Advanced options", open=False): wdtagger_model = gr.Dropdown(label="Original WD Tagger Model", choices=get_wdtagger_models(), value=VIT_LARGE_MODEL_DSV3_REPO) general_threshold = gr.Slider(label="Threshold", minimum=0.0, maximum=1.0, value=0.3, step=0.01, interactive=True) character_threshold = gr.Slider(label="Character threshold", minimum=0.0, maximum=1.0, value=0.8, step=0.01, interactive=True) e621_threshold = gr.Slider(label="Threshold (Z3D-E621-Convnext)", minimum=0.0, maximum=1.0, value=0.5, step=0.01, interactive=True) input_tag_type = gr.Radio(label="Convert tags to", info="danbooru for Animagine, e621 for Pony.", choices=["danbooru", "e621"], value="danbooru") recom_prompt = gr.Radio(label="Insert reccomended prompt", choices=["None", "Animagine", "Pony"], value="None", interactive=True) image_algorithms = gr.CheckboxGroup(["Use WD Tagger", "Use Original WD Tagger", "Use Z3D-E621-Convnext", "Use Florence-2-SD3-Long-Captioner", "Use Florence-2-base-PromptGen"], label="Algorithms", value=["Use WD Tagger"]) keep_tags = gr.Radio(label="Remove tags leaving only the following", choices=["body", "dress", "all"], value="all") generate_from_image_btn = gr.Button(value="GENERATE TAGS FROM IMAGE", size="lg", variant="primary") with gr.Group(): input_character = gr.Textbox(label="Character tags", placeholder="hatsune miku") input_copyright = gr.Textbox(label="Copyright tags", placeholder="vocaloid") random_character = gr.Button(value="Pick a random character 🎲", size="sm") input_general = gr.TextArea(label="General tags", lines=4, placeholder="1girl, ...", value="") input_tags_to_copy = gr.Textbox(value="", visible=False) copy_input_btn = gr.Button(value="Copy to clipboard", size="sm", interactive=False) translate_input_prompt_button = gr.Button(value="Translate prompt to English", size="sm", variant="secondary") tag_type = gr.Radio(label="Output tag conversion", info="danbooru for Animagine, e621 for Pony.", choices=["danbooru", "e621"], value="e621", visible=False) input_rating = gr.Radio(label="Rating", choices=list(V2_RATING_OPTIONS), value="explicit") with gr.Accordion(label="Advanced options", open=False): input_aspect_ratio = gr.Radio(label="Aspect ratio", info="The aspect ratio of the image.", choices=list(V2_ASPECT_RATIO_OPTIONS), value="square") input_length = gr.Radio(label="Length", info="The total length of the tags.", choices=list(V2_LENGTH_OPTIONS), value="very_long") input_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") input_ban_tags = gr.Textbox(label="Ban tags", info="Tags to ban from the output.", placeholder="alternate costumen, ...", value="censored") model_name = gr.Dropdown(label="Model", choices=list(V2_ALL_MODELS.keys()), value=list(V2_ALL_MODELS.keys())[0]) dummy_np = gr.Textbox(label="Negative prompt", value="", visible=False) recom_animagine = gr.Textbox(label="Animagine reccomended prompt", value="Animagine", visible=False) recom_pony = gr.Textbox(label="Pony reccomended prompt", value="Pony", visible=False) generate_btn = gr.Button(value="GENERATE TAGS", size="lg", variant="primary") with gr.Group(): output_text = gr.TextArea(label="Output tags", interactive=False, show_copy_button=True) copy_btn = gr.Button(value="Copy to clipboard", size="sm", interactive=False) elapsed_time_md = gr.Markdown(label="Elapsed time", value="", visible=False) with gr.Group(): output_text_pony = gr.TextArea(label="Output tags (Pony e621 style)", interactive=False, show_copy_button=True) copy_btn_pony = gr.Button(value="Copy to clipboard", size="sm", interactive=False) description_ui2() v2.input_components = [model_name, input_copyright, input_character, input_general, input_rating, input_aspect_ratio, input_length, input_identity, input_ban_tags] random_character.click(select_random_character, [input_copyright, input_character], [input_copyright, input_character], queue=False) translate_input_prompt_button.click(translate_prompt, [input_general], [input_general], queue=False) translate_input_prompt_button.click(translate_prompt, [input_character], [input_character], queue=False) translate_input_prompt_button.click(translate_prompt, [input_copyright], [input_copyright], queue=False) generate_from_image_btn.click( predict_tags_wd, [input_image, input_general, image_algorithms, general_threshold, character_threshold, input_copyright, input_character], [input_copyright, input_character, input_general, copy_input_btn], ).success( predict_tags_wd_large, [input_image, input_general, image_algorithms, general_threshold, character_threshold, input_copyright, input_character, wdtagger_model], [input_copyright, input_character, input_general, copy_input_btn], ).success( predict_tags_e621, [input_image, input_general, image_algorithms, e621_threshold], [input_general], ).success( predict_tags_fl2_sd3, [input_image, input_general, image_algorithms], [input_general], ).success( predict_tags_fl2_base_prompt_gen, [input_image, input_general, image_algorithms], [input_general], ).success( remove_specific_prompt, [input_general, keep_tags], [input_general], queue=False, ).success( convert_danbooru_to_e621_prompt, [input_general, input_tag_type], [input_general], queue=False, ).success( sort_tags, [input_general], [input_general], queue=False, ).success( insert_recom_prompt, [input_general, dummy_np, recom_prompt], [input_general, dummy_np], queue=False, ) copy_input_btn.click(compose_prompt_to_copy, [input_character, input_copyright, input_general], [input_tags_to_copy], queue=False)\ .success(gradio_copy_text, [input_tags_to_copy], js=COPY_ACTION_JS) generate_btn.click( parse_upsampling_output(v2.on_generate), [*v2.input_components], [output_text, elapsed_time_md, copy_btn, copy_btn_pony], ).success( sort_tags, [output_text], [output_text], queue=False, ).success( convert_danbooru_to_e621_prompt, [output_text, tag_type], [output_text_pony], queue=False, ).success( insert_recom_prompt, [output_text, dummy_np, recom_animagine], [output_text, dummy_np], queue=False, ).success( insert_recom_prompt, [output_text_pony, dummy_np, recom_pony], [output_text_pony, dummy_np], queue=False, ) copy_btn.click(gradio_copy_text, [output_text], js=COPY_ACTION_JS) copy_btn_pony.click(gradio_copy_text, [output_text_pony], js=COPY_ACTION_JS) ui.launch() if __name__ == "__main__": main()