Fix VAE dtype mismatch (fp16)

app.py

@@ -215,7 +215,7 @@ from diffusers import UniPCMultistepScheduler, AutoencoderKL, UNet2DConditionMod
 @lru_cache(maxsize=1)
 def get_pipe_and_device() -> Tuple[StableDiffusionXLControlNetImg2ImgPipeline, str, torch.dtype]:
     device = "cuda" if torch.cuda.is_available() else "cpu"
-    dtype = torch.float16 if device == "cuda" else torch.float32
+    dtype = torch.float32 if device == "cuda" else torch.float32
 
     print(f"[PIPE] device={device}, dtype={dtype}", flush=True)
 
@@ -351,10 +351,10 @@ def run_one(paths: Paths, prompt: str, steps: int = DEFAULT_STEPS):
     
  
     if device == "cuda":
-        pipe.to(dtype=torch.float16)
+        pipe.to(dtype=torch.float32)
         try:
             for _, proc in pipe.unet.attn_processors.items():
-                proc.to(dtype=torch.float16)
+                proc.to(dtype=torch.float32)
         except Exception:
             pass