Upload app.py

app.py

@@ -1,14 +1,24 @@
+import os
 import gradio as gr
-from transformers import BlipProcessor, BlipForConditionalGeneration
+from transformers import BlipProcessor ,BlipForConditionalGeneration
 from PIL import Image
+from transformers import CLIPProcessor, ChineseCLIPVisionModel ,AutoProcessor
+
+# 设置环境变量 HF_HOME 和 HF_ENDPOINT
+# os.environ['HF_HOME'] = 'D:/AI/OCR/img2text/models'
+# os.environ['HF_ENDPOINT'] = 'https://hf-mirror.com'
 
-# 加载模型和处理器
-processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
-model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
 
+# model = ChineseCLIPVisionModel.from_pretrained("OFA-Sys/chinese-clip-vit-base-patch16")
+# processor = AutoProcessor.from_pretrained("OFA-Sys/chinese-clip-vit-base-patch16")
+# 加载模型和处理器
+# processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+# model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
+processor = BlipProcessor.from_pretrained("IDEA-CCNL/Taiyi-BLIP-750M-Chinese")
+model = BlipForConditionalGeneration.from_pretrained("IDEA-CCNL/Taiyi-BLIP-750M-Chinese")
 def generate_caption(image):
     inputs = processor(image, return_tensors="pt")
-    outputs = model.generate(**inputs)
+    outputs = model(**inputs)
     description = processor.decode(outputs[0], skip_special_tokens=True)
     return description