removed logger

app.py

@@ -1,19 +1,15 @@
 import torch
-import logging
 from diffusers import DiffusionPipeline
 import gradio as gr
 import numpy as np
-# from PIL import Image, ImageDraw
-import threading
 import openai
 import os
 import spaces
 import base64
-import traceback
 
 # Setup logging
-logging.basicConfig(level=logging.DEBUG)
-logger = logging.getLogger(__name__)
+# logging.basicConfig(level=logging.DEBUG)
+# logger = logging.getLogger(__name__)
 
 # Retrieve the OpenAI API key from the environment
 API_KEY = os.getenv('OPEN_AI_API_KEYS')
@@ -25,12 +21,6 @@ DESCRIPTION = '''
 <p style="text-align: center;">For Instructions on how to use the models <a href="https://huggingface.co/spaces/sandz7/chimera/blob/main/README.md"><b>view this</b></a></p>
 </div>
 '''
-# DESCRIPTION = '''
-# <div>
-# <h1 style="text-align: center;">Chimera Image Generation</h1>
-# <p>This contains a Stable Diffusor from <a href="https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0"><b>stabilityai/stable-diffusion-xl-base-1.0</b></a> and a Multimodal from <a href="https://huggingface.co/xtuner/llava-llama-3-8b-v1_1-transformers"><b>xtuner/llava-llama-3-8b-v1_1-transformers</b></a></p>
-# </div>
-# '''
 
 # load both base and refiner
 base = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16, use_safetensors=True, variant="fp16").to("cuda:0")
@@ -42,10 +32,6 @@ refiner = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-ref
                                             variant="fp16").to("cuda:0")
 
 chat_mode = {}
-# class ChatMode:
-#     def __init__(self):
-#         self.modes = {}
-#         self.current_mode = None
 
 def encode_image(image_path):
     chat_mode["the_mode"] = "diffusing"
@@ -72,7 +58,6 @@ def generation(message, history):
 
     if image_path is None:
         chat_mode["mode"] = "text"
-        # input_prompt = message if isinstance(message, str) else message.get("text", "")
         client = openai.OpenAI(api_key=API_KEY)
         stream = client.chat.completions.create(
             model="gpt-3.5-turbo",
@@ -83,7 +68,6 @@ def generation(message, history):
         return stream
     else:
         chat_mode["mode"] = "image"
-        # input_prompt = message if isinstance(message, str) else message.get("text", "")
         base64_image = encode_image(image_path=image_path)
         client = openai.OpenAI(api_key=API_KEY)
         stream = client.chat.completions.create(
@@ -110,50 +94,21 @@ def diffusing(prompt: str,
     """
 
     # Generate image based on text
-    try:
-        logger.debug(f"Running diffusing with prompt: {prompt}, n_steps: {n_steps}, denoising: {denoising}")
-
-        # Generate image based on text
-        logger.debug("Calling base() function.")
-        image_base = base(
-            prompt=prompt,
-            num_inference_steps=n_steps,
-            denoising_end=denoising,
-            output_type="latent"
-        ).images
-
-        logger.debug("Base image generated successfully. Proceeding to refiner.")
-
-        logger.debug("Calling refiner() function.")
-        image = refiner(
-            prompt=prompt,
-            num_inference_steps=n_steps,
-            denoising_start=denoising,
-            image=image_base
-        ).images[0]
-
-        logger.debug("Refined image generated successfully.")
-        
-        return image
-
-    except Exception as e:
-        logger.error(f"Error in diffusing: {str(e)}")
-        logger.error(traceback.format_exc())
-        raise
-    # image_base = base(
-    #     prompt=prompt,
-    #     num_inference_steps=n_steps,
-    #     denoising_end=denoising,
-    #     output_type="latent"
-    # ).images
-    # image = refiner(
-    #     prompt=prompt,
-    #     num_inference_steps=n_steps,
-    #     denoising_start=denoising,
-    #     image=image_base
-    # ).images[0]
-
-    # return image
+    image_base = base(
+        prompt=prompt,
+        num_inference_steps=n_steps,
+        denoising_end=denoising,
+        output_type="latent"
+    ).images
+
+    image = refiner(
+        prompt=prompt,
+        num_inference_steps=n_steps,
+        denoising_start=denoising,
+        image=image_base
+    ).images[0]
+    
+    return image
     
 def check_cuda_availability():
     if torch.cuda.is_available():
@@ -175,7 +130,6 @@ def bot_comms(message, history):
         message = {"text": message}
 
     if message["text"] == "check cuda":
-        logger.debug("Checking CUDA availability.")
         yield check_cuda_availability()
         return