Update app.py

app.py

@@ -3,13 +3,10 @@ from diffusers import StableDiffusionPipeline
 import torch
 
 # --- Configuration ---
-# Your Hugging Face repository ID where the LoRAs are stored
 HF_REPO_ID = "aanchal77/Final-One" 
 BASE_MODEL_ID = "runwayml/stable-diffusion-v1-5"
 
-# --- Define Available LoRAs from your HF Repo ---
-# The key is the display name in the dropdown.
-# The value is the subfolder path inside your Hugging Face repository.
+# --- Define Available LoRAs ---
 AVAILABLE_LORAS = {
     "None (Base Model)": None,
     # --- Artists ---
@@ -33,43 +30,13 @@ device = "cuda" if torch.cuda.is_available() else "cpu"
 dtype = torch.float16 if device == "cuda" else torch.float32
 print(f"Using device: {device}")
 
-# --- Load the Base Model ---
-# This will be cached in the Space for faster startups.
 print(f"🎨 Loading base model: {BASE_MODEL_ID}")
 pipe = StableDiffusionPipeline.from_pretrained(BASE_MODEL_ID, torch_dtype=dtype).to(device)
 if device == "cpu":
     pipe.enable_attention_slicing()
 
 # --- The Core Generation Function ---
-# def generate(prompt, quality, lora_choice):
-#     """
-#     Generates an image, dynamically loading the selected LoRA from the Hub.
-#     """
-#     # Unload any existing LoRA to reset to the base model
-#     pipe.unload_lora_weights()
-    
-#     lora_subfolder = AVAILABLE_LORAS.get(lora_choice)
-
-#     if lora_subfolder:
-#         print(f"✨ Downloading and applying LoRA: {lora_choice}")
-#         try:
-#             # Load LoRA directly from the Hugging Face Hub
-#             pipe.load_lora_weights(HF_REPO_ID, subfolder=lora_subfolder)
-#         except Exception as e:
-#             print(f"❌ Failed to load LoRA from Hub '{HF_REPO_ID}/{lora_subfolder}': {e}")
-#     else:
-#         print("🎨 Using base model (no LoRA selected)")
-
-#     steps = 25 if quality == "Fast" else 40
-#     guidance_scale = 7.5
-    
-#     print(f"🚀 Generating with prompt: '{prompt}'")
-#     with torch.no_grad():
-#         image = pipe(prompt, num_inference_steps=steps, guidance_scale=guidance_scale).images[0]
-        
-#     return image
 def generate(prompt, quality, lora_choice):
-    # Reset to base model
     pipe.unload_lora_weights()
     
     lora_subfolder = AVAILABLE_LORAS.get(lora_choice)
@@ -80,7 +47,7 @@ def generate(prompt, quality, lora_choice):
             pipe.load_lora_weights(
                 HF_REPO_ID,
                 subfolder=lora_subfolder,
-                weight_name="adapter_model.safetensors"  # 👈 specify the file
+                weight_name="adapter_model.safetensors"  # ✅ Explicit LoRA file
             )
         except Exception as e:
             print(f"❌ Failed to load LoRA from Hub '{HF_REPO_ID}/{lora_subfolder}': {e}")
@@ -96,7 +63,6 @@ def generate(prompt, quality, lora_choice):
         
     return image
 
-
 # --- Build the Gradio UI ---
 title = f"🎨 Stable Diffusion Gallery from {HF_REPO_ID}"
 description = "Select a trained LoRA model from your Hugging Face repository to apply its style. The first time you select a LoRA, it may take a moment to download."