chore: fix code

README.md

@@ -262,4 +262,26 @@ This will:
 1. Send a request to your endpoint
 2. Download the generated image
 3. Save it to the specified output directory
-4. Display the seed used for generation 
+4. Display the seed used for generation 
+
+## Troubleshooting
+
+### Error: "You are trying to load the model files of the `variant=fp16`, but no such modeling files are available"
+
+If you encounter this error when deploying your endpoint, it means the model you're trying to use doesn't have an fp16 variant explicitly available. To fix this:
+
+1. Open `handler.py`
+2. Find the `StableDiffusionXLPipeline.from_pretrained` call
+3. Remove the `variant="fp16"` parameter
+
+The corrected code should look like:
+```python
+pipe = StableDiffusionXLPipeline.from_pretrained(
+    ckpt_dir,
+    vae=vae,
+    torch_dtype=torch.float16,
+    use_safetensors=self.cfg.get("use_safetensors", True)
+)
+```
+
+This change allows the model to be loaded with fp16 precision without requiring a specific fp16 variant of the model weights. 

handler.py

@@ -103,8 +103,7 @@ class EndpointHandler:
             ckpt_dir,
             vae=vae,
             torch_dtype=torch.float16,
-            use_safetensors=self.cfg.get("use_safetensors", True),
-            variant="fp16"
+            use_safetensors=self.cfg.get("use_safetensors", True)
         )
         # Move model to GPU
         pipe = pipe.to("cuda")