Update README_sdxl.md

Author: nprabhakar

examples/dreambooth/README_sdxl.md

@@ -87,7 +87,6 @@ accelerate launch train_dreambooth_lora_sdxl.py \
   --train_batch_size=1 \
   --gradient_accumulation_steps=4 \
   --learning_rate=1e-4 \
-  --report_to="wandb" \
   --lr_scheduler="constant" \
   --lr_warmup_steps=0 \
   --max_train_steps=500 \
@@ -272,4 +271,4 @@ The inference is the same as if you train a regular LoRA 🤗
 
 ## Format compatibility
 
-You can pass `--output_kohya_format` to additionally generate a state dictionary which should be compatible with other platforms and tools such as Automatic 1111, Comfy, Kohya, etc. The `output_dir` will contain a file named "pytorch_lora_weights_kohya.safetensors".
+You can pass `--output_kohya_format` to additionally generate a state dictionary which should be compatible with other platforms and tools such as Automatic 1111, Comfy, Kohya, etc. The `output_dir` will contain a file named "pytorch_lora_weights_kohya.safetensors".