sdxl-based/realvisxl-v3-multi-controlnet-lora

Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.

Random seed. Leave blank to randomize the seed

Input image for img2img or inpaint mode

Width of output image

Height of output image

Input prompt

Which refine style to use

scheduler

LoRA additive scale. Only applicable on trained models.

Number of images to output

Controlnet

Controlnet

Controlnet

Replicate LoRA weights to use. Leave blank to use the default weights.

For base_image_refiner, the number of steps to refine, defaults to num_inference_steps

Scale for classifier-free guidance

Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.

Negative Prompt

Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image

Decide how to resize images – use width/height, resize based on input image or control image

When controlnet conditioning ends

When controlnet conditioning ends

When controlnet conditioning ends

Input image for first controlnet

When controlnet conditioning starts

Input image for second controlnet

When controlnet conditioning starts

Input image for third controlnet

When controlnet conditioning starts

Number of denoising steps

Disable safety checker for generated images. This feature is only available through the API.

How strong the controlnet conditioning is

How strong the controlnet conditioning is

How strong the controlnet conditioning is