Remove unused code

app.py

@@ -26,10 +26,7 @@ model_id = "sd-legacy/stable-diffusion-v1-5"
 scheduler = EulerDiscreteScheduler.from_pretrained(model_id, subfolder="scheduler")
 
 # Load the image-to-text pipeline with BLIP model
-get_itt_completion = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
-
-# Text-to-image endpoint
-#get_tti_completion = pipeline("text-to-image", model="stabilityai/stable-diffusion-xl-base-1.0")
+get_completion = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
 
 # Load the Stable Diffusion pipeline
 pipe = StableDiffusionPipeline.from_pretrained(
@@ -40,39 +37,24 @@ pipe = StableDiffusionPipeline.from_pretrained(
 )
 pipe = pipe.to(device)
 
-
-# Bringing the functions from lessons 3 and 4!
-def image_to_base64_str(pil_image):
-    byte_arr = io.BytesIO()
-    pil_image.save(byte_arr, format='PNG')
-    byte_arr = byte_arr.getvalue()
-    return str(base64.b64encode(byte_arr).decode('utf-8'))
-
-def base64_to_pil(img_base64):
-    base64_decoded = base64.b64decode(img_base64)
-    byte_stream = io.BytesIO(base64_decoded)
-    pil_image = Image.open(byte_stream)
-    return pil_image
-
 # Caption generate function
-@spaces.GPU # Designed to be effect-free in non-ZeroGPU environments, ensuring compatibility across different setups.
+@spaces.GPU(duration=120) # Designed to be effect-free in non-ZeroGPU environments, ensuring compatibility across different setups.
 def captioner(image):
-    #base64_image = image_to_base64_str(image)
     # The BLIP model expects a PIL image directly
-    result = get_itt_completion(image)
-    #result = get_completion(base64_image, None, ITT_ENDPOINT)
+    result = get_completion(image)
     
     return result[0]['generated_text']
 
 # Image generate function
-@spaces.GPU # Designed to be effect-free in non-ZeroGPU environments, ensuring compatibility across different setups.
+@spaces.GPU(duration=120) # Designed to be effect-free in non-ZeroGPU environments, ensuring compatibility across different setups.
 def generate(prompt, steps):  
-    # Generate image with Stable Diffusion
+    # Generate an image with Stable Diffusion
     output = pipe(
         prompt,
         negative_prompt=None,  # Handle empty negative prompt
         num_inference_steps=25,
     )
+
     return output.images[0]  # Return the first generated image (PIL format)