Update app.py

app.py

@@ -15,7 +15,6 @@ import base64
 from flask import Flask, request, jsonify
 from concurrent.futures import ThreadPoolExecutor
 from flask_cors import CORS
-from tqdm import tqdm
 
 # Configure logging
 logging.basicConfig(level=logging.INFO)
@@ -69,25 +68,25 @@ else:
 logger.info("Hugging Face token: %s", huggingface_token)
 
 # Download model using snapshot_download
-#with tqdm(total=100, desc="Downloading model", bar_format="{l_bar}{bar}| {n_fmt}/{total_fmt}") as pbar:
+
 model_path = snapshot_download(
         repo_id="black-forest-labs/FLUX.1-dev", 
         repo_type="model", 
         ignore_patterns=["*.md", "*..gitattributes"],
         local_dir="FLUX.1-dev",
         token=huggingface_token)
-    logger.info("Model downloaded to: %s", model_path)
+logger.info("Model downloaded to: %s", model_path)
 
 # Load pipeline
 logger.info('Loading ControlNet model.')
-#with tqdm(total=100, desc="Downloading ControlNet model", bar_format="{l_bar}{bar}| {n_fmt}/{total_fmt}") as pbar:
+
 controlnet = FluxControlNetModel.from_pretrained(
         "jasperai/Flux.1-dev-Controlnet-Upscaler", torch_dtype=torch.bfloat16
     ).to(device)
 logger.info("ControlNet model loaded successfully.")
 
 logger.info('Loading pipeline.')
-#with tqdm(total=100, desc="Downloading pipeline", bar_format="{l_bar}{bar}| {n_fmt}/{total_fmt}") as pbar:
+
 pipe = FluxControlNetPipeline.from_pretrained(
         model_path, controlnet=controlnet, torch_dtype=torch.bfloat16
     ).to(device)
@@ -157,40 +156,6 @@ def run_inference(process_id, input_image, upscale_factor, seed, num_inference_s
     app.config['image_outputs'][process_id] = image_base64
     logger.info("Inference completed for process_id: %s", process_id)
 
-# @app.route('/infer', methods=['POST'])
-# def infer():
-#     data = request.json
-#     seed = data.get("seed", 42)
-#     randomize_seed = data.get("randomize_seed", True)
-#     num_inference_steps = data.get("num_inference_steps", 28)
-#     upscale_factor = data.get("upscale_factor", 4)
-#     controlnet_conditioning_scale = data.get("controlnet_conditioning_scale", 0.6)
-
-#     # Randomize seed if specified
-#     if randomize_seed:
-#         seed = random.randint(0, MAX_SEED)
-#         logger.info("Seed randomized to: %d", seed)
-
-#     # Load and process the input image
-#     input_image_data = base64.b64decode(data['input_image'])
-#     input_image = Image.open(io.BytesIO(input_image_data))
-
-#     # Create a unique process ID for this request
-#     process_id = str(random.randint(1000, 9999))
-#     logger.info("Process started with process_id: %s", process_id)
-
-#     # Set the status to 'in_progress'
-#     app.config['image_outputs'][process_id] = None
-
-    # # Run the inference in a separate thread
-    # executor.submit(run_inference, process_id, input_image, upscale_factor, seed, num_inference_steps, controlnet_conditioning_scale)
-
-    # # Return the process ID
-    # return jsonify({
-    #     "process_id": process_id,
-    #     "message": "Processing started"
-    # })
-
 @app.route('/infer', methods=['POST'])
 def infer():
     # Check if the file was provided in the form-data
@@ -216,7 +181,6 @@ def infer():
     input_image = Image.open(file)
     buffered = io.BytesIO()
     input_image.save(buffered, format="JPEG")
-    #input_image_base64 = base64.b64encode(buffered.getvalue()).decode("utf-8")
 
     # Retrieve additional parameters from the request (if any)
     seed = request.form.get("seed", 42, type=int)