Upload 13 files

app.py

@@ -21,6 +21,7 @@ from tagger.tagger import (
     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 (
@@ -40,12 +41,12 @@ load_models(models, 5)
 
 
 css = """
-#model_info { text-align: center; display:block; }
+#model_info { text-align: center; }
 """
 
 with gr.Blocks(theme="NoCrypt/miku@>=1.2.2", css=css) as demo:
     with gr.Column(): 
-        with gr.Accordion("Advanced settings", open=True):
+        with gr.Accordion("Advanced settings", open=False):
             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():
@@ -61,6 +62,7 @@ with gr.Blocks(theme="NoCrypt/miku@>=1.2.2", css=css) as demo:
                 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)
             with gr.Accordion("Model", open=True):
                 model_name = gr.Dropdown(label="Select Model", show_label=False, 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_id="model_info")
@@ -142,9 +144,11 @@ with gr.Blocks(theme="NoCrypt/miku@>=1.2.2", css=css) as demo:
         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, gr.Button(visible=False)],
+        [v2_series, v2_character, prompt, v2_copy],
         show_api=False,
     ).success(
         predict_tags_fl2_sd3, [tagger_image, prompt, tagger_algorithms], [prompt], show_api=False,
@@ -154,6 +158,8 @@ with gr.Blocks(theme="NoCrypt/miku@>=1.2.2", css=css) as demo:
         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()

requirements.txt

@@ -1,5 +1,5 @@
 huggingface_hub
-torch
+torch==2.2.0
 torchvision
 accelerate
 transformers

tagger/fl2sd3longcap.py

@@ -2,11 +2,13 @@ from transformers import AutoProcessor, AutoModelForCausalLM
 import spaces
 import re
 from PIL import Image 
+import torch
 
 import subprocess
 subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
 
-fl_model = AutoModelForCausalLM.from_pretrained('gokaygokay/Florence-2-SD3-Captioner', trust_remote_code=True).eval()
+device = "cuda" if torch.cuda.is_available() else "cpu"
+fl_model = AutoModelForCausalLM.from_pretrained('gokaygokay/Florence-2-SD3-Captioner', trust_remote_code=True).to(device).eval()
 fl_processor = AutoProcessor.from_pretrained('gokaygokay/Florence-2-SD3-Captioner', trust_remote_code=True)
 
 
@@ -48,7 +50,7 @@ def fl_run_example(image):
     if image.mode != "RGB":
         image = image.convert("RGB")
 
-    inputs = fl_processor(text=prompt, images=image, return_tensors="pt")
+    inputs = fl_processor(text=prompt, images=image, return_tensors="pt").to(device)
     generated_ids = fl_model.generate(
         input_ids=inputs["input_ids"],
         pixel_values=inputs["pixel_values"],

tagger/utils.py

@@ -43,3 +43,8 @@ COPY_ACTION_JS = """\
     navigator.clipboard.writeText(inputs);
   }
 }"""
+
+
+def gradio_copy_prompt(prompt: str):
+    gr.Info("Copied!")
+    return prompt