Trying fix variants

app.py

@@ -6,21 +6,20 @@ from transformers import DPTFeatureExtractor, DPTForDepthEstimation
 from PIL import Image, ImageEnhance, ImageOps
 
 # Configuração de dispositivo
-device = "cuda" if torch.cuda.is_available() else "cpu"
-torch_dtype = torch.float32 if device == "cpu" else torch.float16
+device = "cpu"  # or "cuda" if you have a GPU
+torch_dtype = torch.float32
 
 print("Carregando modelo SDXL Img2Img...")
 pipe = StableDiffusionXLImg2ImgPipeline.from_pretrained(
     "stabilityai/stable-diffusion-xl-base-1.0",
-    torch_dtype=torch_dtype,
-    use_safetensors=True
+    torch_dtype=torch_dtype
 ).to(device)
 
-print("Carregando pesos LoRA...")
+print("Carregando pesos LoRA weights with PEFT...")
 pipe.load_lora_weights(
     "KappaNeuro/bas-relief",
     weight_name="BAS-RELIEF.safetensors",
-    adapter_name="bas_relief"
+    peft_backend="peft"
 )
 
 print("Carregando modelo de profundidade...")
@@ -50,13 +49,15 @@ def processar_imagem(imagem: Image.Image):
 
     # Calcular profundidade
     inputs = feature_extractor(resultado.images[0], return_tensors="pt").to(device)
-    with torch.no_grad():
-        depth = depth_model(**inputs).predicted_depth
+    with (torch.no_grad()):
+        outputs  = depth_model(**inputs)
+        predicted_depth = outputs.predicted_depth
 
     depth_map = torch.nn.functional.interpolate(
-        depth.unsqueeze(1),
+        predicted_depth.unsqueeze(1),
         size=imagem.size[::-1],
-        mode="bicubic"
+        mode="bicubic",
+        align_corners=False
     ).squeeze().cpu().numpy()
 
     return resultado.images[0], processar_profundidade(depth_map)