Update app.py

app.py

@@ -5,17 +5,16 @@ from diffusers import AutoPipelineForText2Image
 from io import BytesIO
 import gradio as gr
 from concurrent.futures import ProcessPoolExecutor
-import multiprocessing
 
-# Load the model once outside of the function and share across processes
+# Load the model once outside of the function
 print("Loading the model...")
 model = AutoPipelineForText2Image.from_pretrained("stabilityai/sdxl-turbo")
 print("Model loaded successfully.")
 
-def generate_image(prompt, prompt_name, num_inference_steps=1):
+def generate_image(prompt, prompt_name):
     try:
         print(f"Generating response for {prompt_name} with prompt: {prompt}")
-        output = model(prompt=prompt, num_inference_steps=num_inference_steps, guidance_scale=0.0)
+        output = model(prompt=prompt, num_inference_steps=1, guidance_scale=0.0)
         print(f"Output for {prompt_name}: {output}")
 
         # Check if the model returned images
@@ -44,12 +43,12 @@ async def queue_api_calls(sentence_mapping, character_dict, selected_style):
     for paragraph_number, sentences in sentence_mapping.items():
         combined_sentence = " ".join(sentences)
         print(f"combined_sentence for paragraph {paragraph_number}: {combined_sentence}")
-        prompt = generate_prompt(combined_sentence, sentence_mapping, character_dict, selected_style)
+        prompt = generate_prompt(combined_sentence, character_dict, selected_style)
         prompts.append((paragraph_number, prompt))
         print(f"Generated prompt for paragraph {paragraph_number}: {prompt}")
 
-    # Set max_workers to the minimum of the number of prompts and available CPU cores
-    max_workers = min(len(prompts), multiprocessing.cpu_count())
+    # Set max_workers to the total number of prompts
+    max_workers = len(prompts)
 
     # Generate images for each prompt in parallel using multiprocessing
     with ProcessPoolExecutor(max_workers=max_workers) as executor:
@@ -66,12 +65,15 @@ async def queue_api_calls(sentence_mapping, character_dict, selected_style):
 def process_prompt(sentence_mapping, character_dict, selected_style):
     print(f"process_prompt called with sentence_mapping: {sentence_mapping}, character_dict: {character_dict}, selected_style: {selected_style}")
     try:
+        # See if there is a loop already running. If there is, reuse it.
         loop = asyncio.get_running_loop()
     except RuntimeError:
+        # Create new event loop if one is not running
         loop = asyncio.new_event_loop()
         asyncio.set_event_loop(loop)
     print("Event loop created.")
 
+    # This sends the prompts to function that sets up the async calls. Once all the calls to the API complete, it returns a list of the gr.Textbox with value= set.
     cmpt_return = loop.run_until_complete(queue_api_calls(sentence_mapping, character_dict, selected_style))
     print(f"process_prompt completed with return value: {cmpt_return}")
     return cmpt_return
@@ -89,5 +91,5 @@ gradio_interface = gr.Interface(
 
 if __name__ == "__main__":
     print("Launching Gradio interface...")
-    gradio_interface.launch(server_name="0.0.0.0", server_port=7860, debug=True)
+    gradio_interface.launch()
     print("Gradio interface launched.")