Update app.py

app.py

@@ -35,14 +35,8 @@ processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-larg
 model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")
 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")
+pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-3.5-medium")
 
-pipe3 = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev")
-pipe3.load_lora_weights("tryonlabs/FLUX.1-dev-LoRA-Outfit-Generator")
 
 
 
@@ -51,7 +45,7 @@ device = "cuda" if torch.cuda.is_available() else "cpu"
 # pipe.to(device)
 model2.to(device)
 model.to(device)
-pip3.to(device)
+pip.to(device)
 
 
 
@@ -61,28 +55,6 @@ def generate_caption_and_image(image):
     # 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
-    # )
-    
 
 
         
@@ -99,7 +71,7 @@ def generate_caption_and_image(image):
     text = "a picture of "
     inputs = processor(img, text, return_tensors="pt").to(device)
     
-    out = model.generate(**inputs, num_beams = 3)
+    out = model2.generate(**inputs, num_beams = 3)
    
     
 
@@ -116,7 +88,7 @@ def generate_caption_and_image(image):
   
 
     # Generate image based on the caption
-    generated_image = pipe3(prompt).images[0]
+    generated_image = pipe(prompt).images[0]
 
     return prompt, generated_image