This workflow is optimized for a 4-bit quantized model using the Nunchaku Node. If you prefer, you can easily use a regular UNET or AIO model with the standard nodes you're used to.

Here are a few tips to get the best results:

• Redux Settings: Feel free to experiment with the Redux settings to find what works best for your image.

• Turbo LoRA: The Turbo LoRA is included for faster generation, but it's completely optional. If you want more detail in your image, just bypass this LoRA and increase your sampling steps.

• Adding LoRAs: To add your own LoRAs, simply load them into the LoRA Loader and remember to include their specific trigger words in the LoRA Trigger Word text area.

• Custom Latent Size: The Image Size node is a helpful starting point, but you have full control! You can disable it and adjust the latent size directly to get the exact dimensions you need.