Update app.py

app.py

@@ -1,77 +1,60 @@
 import gradio as gr
 from diffusers import AutoPipelineForText2Image
-from generate_propmts import generate_prompt
+from transformers import AutoTokenizer
 from PIL import Image
 import asyncio
-import threading
-import traceback
-
-# Load the model once outside of the function
-model = AutoPipelineForText2Image.from_pretrained("stabilityai/sdxl-turbo")
 
 class SchedulerWrapper:
     def __init__(self, scheduler):
         self.scheduler = scheduler
-        self._step = threading.local()
-        self._step.step = 0
+        
+    def __getattr__(self, name):
+        return getattr(self.scheduler, name)
+        
+    @property
+    def timesteps(self):
+        return self.scheduler.timesteps
 
-    def step(self, *args, **kwargs):
-        try:
-            self._step.step += 1
-            return self.scheduler.step(*args, **kwargs)
-        except IndexError:
-            self._step.step = 0
-            return self.scheduler.step(*args, **kwargs)
-    
-    def set_timesteps(self, *args, **kwargs):
-        return self.scheduler.set_timesteps(*args, **kwargs)
+    def set_timesteps(self, timesteps):
+        self.scheduler.set_timesteps(timesteps)
+
+# Load the model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("stabilityai/sdxl-turbo")
+model = AutoPipelineForText2Image.from_pretrained("stabilityai/sdxl-turbo")
 
 # Wrap the scheduler
-model.scheduler = SchedulerWrapper(model.scheduler)
+scheduler = model.scheduler
+wrapped_scheduler = SchedulerWrapper(scheduler)
+model.scheduler = wrapped_scheduler
 
 async def generate_image(prompt):
     try:
-        # Set a higher value for num_inference_steps
-        num_inference_steps = 5  # Adjust this value as needed
-
-        # Use the model to generate an image
+        num_inference_steps = 5
         output = await asyncio.to_thread(
             model,
             prompt=prompt,
             num_inference_steps=num_inference_steps,
-            guidance_scale=0.0,  # Typical value for guidance scale in image generation
-            output_type="pil"  # Directly get PIL Image objects
+            guidance_scale=0.0,
+            output_type="pil"
         )
-
-        # Check for output validity and return
         if output.images:
             return output.images[0]
         else:
             raise Exception("No images returned by the model.")
     except Exception as e:
         print(f"Error generating image: {e}")
-        traceback.print_exc()
-        return None  # Return None on error to handle it gracefully in the UI
+        return None
 
 async def inference(sentence_mapping, character_dict, selected_style):
     images = []
-    print(f'sentence_mapping: {sentence_mapping}, character_dict: {character_dict}, selected_style: {selected_style}')
     prompts = []
-
-    # Generate prompts for each paragraph
     for paragraph_number, sentences in sentence_mapping.items():
         combined_sentence = " ".join(sentences)
         prompt = generate_prompt(combined_sentence, sentence_mapping, character_dict, selected_style)
         prompts.append(prompt)
-        print(f"Generated prompt for paragraph {paragraph_number}: {prompt}")
-
-    # Use asyncio.gather to run generate_image in parallel
     tasks = [generate_image(prompt) for prompt in prompts]
     images = await asyncio.gather(*tasks)
-
-    # Filter out None values
     images = [image for image in images if image is not None]
-
     return images
 
 gradio_interface = gr.Interface(