Update app.py

app.py

@@ -10,9 +10,9 @@ import torch
 import uuid
 from diffusers import Flux2Pipeline, Flux2Transformer2DModel
 from diffusers import BitsAndBytesConfig as DiffBitsAndBytesConfig
-import requests
+# import requests
 from PIL import Image
-import json
+# import json
 import base64
 from huggingface_hub import InferenceClient
 import logging
@@ -33,10 +33,10 @@ device = "cuda" if torch.cuda.is_available() else "cpu"
 MAX_SEED = np.iinfo(np.int32).max
 MAX_IMAGE_SIZE = 1024
 
-hf_client = InferenceClient(
-    api_key=os.environ.get("HF_TOKEN"),
-)
-VLM_MODEL = "baidu/ERNIE-4.5-VL-424B-A47B-Base-PT"
+# hf_client = InferenceClient(
+#     api_key=os.environ.get("HF_TOKEN"),
+# )
+# VLM_MODEL = "baidu/ERNIE-4.5-VL-424B-A47B-Base-PT"
 
 SYSTEM_PROMPT_TEXT_ONLY = """You are an expert prompt engineer for FLUX.2 by Black Forest Labs. Rewrite user prompts to be more descriptive while strictly preserving their core subject and intent.
 Guidelines:
@@ -132,44 +132,44 @@ def image_to_data_uri(img):
     img_str = base64.b64encode(buffered.getvalue()).decode("utf-8")
     return f"data:image/png;base64,{img_str}"
 
-def upsample_prompt_logic(prompt, image_list):
-    try:
-        if image_list and len(image_list) > 0:
-            # Image + Text Editing Mode
-            system_content = SYSTEM_PROMPT_WITH_IMAGES
+# def upsample_prompt_logic(prompt, image_list):
+#     try:
+#         if image_list and len(image_list) > 0:
+#             # Image + Text Editing Mode
+#             system_content = SYSTEM_PROMPT_WITH_IMAGES
             
-            # Construct user message with text and images
-            user_content = [{"type": "text", "text": prompt}]
+#             # Construct user message with text and images
+#             user_content = [{"type": "text", "text": prompt}]
             
-            for img in image_list:
-                data_uri = image_to_data_uri(img)
-                user_content.append({
-                    "type": "image_url",
-                    "image_url": {"url": data_uri}
-                })
+#             for img in image_list:
+#                 data_uri = image_to_data_uri(img)
+#                 user_content.append({
+#                     "type": "image_url",
+#                     "image_url": {"url": data_uri}
+#                 })
                 
-            messages = [
-                {"role": "system", "content": system_content},
-                {"role": "user", "content": user_content}
-            ]
-        else:
-            # Text Only Mode
-            system_content = SYSTEM_PROMPT_TEXT_ONLY
-            messages = [
-                {"role": "system", "content": system_content},
-                {"role": "user", "content": prompt}
-            ]
-
-        completion = hf_client.chat.completions.create(
-            model=VLM_MODEL,
-            messages=messages,
-            max_tokens=1024
-        )
+#             messages = [
+#                 {"role": "system", "content": system_content},
+#                 {"role": "user", "content": user_content}
+#             ]
+#         else:
+#             # Text Only Mode
+#             system_content = SYSTEM_PROMPT_TEXT_ONLY
+#             messages = [
+#                 {"role": "system", "content": system_content},
+#                 {"role": "user", "content": prompt}
+#             ]
+
+#         completion = hf_client.chat.completions.create(
+#             model=VLM_MODEL,
+#             messages=messages,
+#             max_tokens=1024
+#         )
         
-        return completion.choices[0].message.content
-    except Exception as e:
-        print(f"Upsampling failed: {e}")
-        return prompt
+#         return completion.choices[0].message.content
+#     except Exception as e:
+#         print(f"Upsampling failed: {e}")
+#         return prompt
 
 def update_dimensions_from_image(image_list, width, height):
     """Update width/height sliders based on uploaded image aspect ratio.