Update app.py

app.py

@@ -34,10 +34,10 @@ model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-capt
 processor1 = BlipProcessor.from_pretrained("noamrot/FuseCap")
 model2 = BlipForConditionalGeneration.from_pretrained("noamrot/FuseCap")
 pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-3.5-medium")
-model3 =model = Qwen2VLForConditionalGeneration.from_pretrained(
-    "prithivMLmods/Qwen2-VL-OCR-2B-Instruct", torch_dtype="auto", device_map="auto"
-)
-processor2 = AutoProcessor.from_pretrained("prithivMLmods/Qwen2-VL-OCR-2B-Instruct")
+# model3 =model = Qwen2VLForConditionalGeneration.from_pretrained(
+#     "prithivMLmods/Qwen2-VL-OCR-2B-Instruct", torch_dtype="auto", device_map="auto"
+# )
+# processor2 = AutoProcessor.from_pretrained("prithivMLmods/Qwen2-VL-OCR-2B-Instruct")
 
 
 
@@ -53,29 +53,29 @@ model.to(device)
 def generate_caption_and_image(image):
     img = image.convert("RGB")
     # reader = easyocr.Reader(['en'])  
-    # result = reader.readtext(img)
-    import random
-    messages = [{"role": "user", "content": [{"type": "image", "image": img}, {"type": "text", "text": "Describe this Image"}]}]
-
-    text = processor.apply_chat_template(
-        messages, tokenize=False, add_generation_prompt=True
-    )
-    image_inputs, video_inputs = process_vision_info(messages)
-    inputs = processor(
-        text=[text],
-        images=image_inputs,
-        videos=video_inputs,
-        padding=True,
-        return_tensors="pt",
-    )
-    inputs = inputs.to(device)
-    generated_ids = model.generate(**inputs, max_new_tokens=128)
-    generated_ids_trimmed = [
-        out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
-    ]
-    result = processor.batch_decode(
-        generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
-    )
+    # # result = reader.readtext(img)
+    # import random
+    # messages = [{"role": "user", "content": [{"type": "image", "image": img}, {"type": "text", "text": "Describe this Image"}]}]
+
+    # text = processor.apply_chat_template(
+    #     messages, tokenize=False, add_generation_prompt=True
+    # )
+    # image_inputs, video_inputs = process_vision_info(messages)
+    # inputs = processor(
+    #     text=[text],
+    #     images=image_inputs,
+    #     videos=video_inputs,
+    #     padding=True,
+    #     return_tensors="pt",
+    # )
+    # inputs = inputs.to(device)
+    # generated_ids = model.generate(**inputs, max_new_tokens=128)
+    # generated_ids_trimmed = [
+    #     out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+    # ]
+    # result = processor.batch_decode(
+    #     generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
+    # )
     
 
 
@@ -105,7 +105,7 @@ def generate_caption_and_image(image):
     out = model.generate(**inputs)
     caption1 = processor.decode(out[0], skip_special_tokens=True)
 
-    prompt = f'''Create a highly realistic clothing item based on the following descriptions: The design should reflect {caption1} and {caption2}, blending both themes into a single, stylish, and modern piece of clothing. Incorporate highly realistic and high-quality textures that exude sophistication, with realistic fabric lighting and fine details. Subtly hint at {selected_fabric}, featuring a {selected_pattern} motif and a {selected_textile_design} style that harmoniously balances the essence of both captions.and {result} should be written on top of it'''
+    prompt = f'''Create a highly realistic clothing item based on the following descriptions: The design should reflect {caption1} and {caption2}, blending both themes into a single, stylish, and modern piece of clothing. Incorporate highly realistic and high-quality textures that exude sophistication, with realistic fabric lighting and fine details. Subtly hint at {selected_fabric}, featuring a {selected_pattern} motif and a {selected_textile_design} style that harmoniously balances the essence of both captions.'''