Upload 9 files

app.py

@@ -143,6 +143,8 @@ 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,
+    ).success(
         predict_tags_wd,
         [tagger_image, prompt, tagger_algorithms, tagger_general_threshold, tagger_character_threshold],
         [v2_series, v2_character, prompt, v2_copy],

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"],