Trainzone - AI Prompts & LoRA Marketplace

Modelsbytedancesdxl-lightning-4step

1,029,788,371 runs3/17/2025

SDXL-Lightning by ByteDance: a fast text-to-image model that makes high-quality images in 4 steps

Input

Prompt

Input prompt

Negative Prompt

Negative Input prompt

Width

Width of output image. Recommended 1024 or 1280

Height

Height of output image. Recommended 1024 or 1280

Num Outputs

Number of images to output.

scheduler

Num Inference Steps

Number of denoising steps. 4 for best results

Guidance Scale

Scale for classifier-free guidance

Seed

Random seed. Leave blank to randomize the seed

Disable Safety Checker

Disabled

Disable safety checker for generated images

Configure the model parameters in the sidebar and click Run to generate content.