PeterL1n's picture
Publish model
77c78cc
metadata
license: openrail++
tags:
  - stable-diffusion
  - text-to-image

SD v2.1-base with Zero Terminal SNR (LAION Aesthetic 5+)

This is the official model for Common Diffusion Noise Schedules and Sample Steps are Flawed paper.

This model is trained using the zero terminal SNR schedule on LAION aesthetic 5+ data.

This model is finetuned from stabilityai/stable-diffusion-2-1-base.

This model is meant for research demonstration, not for production use.

Usage

from diffusers import StableDiffusionPipeline
prompt = "A young girl smiling"
pipe = StableDiffusionPipeline.from_pretrained("ByteDance/sd2.1-base-zsnr-laionaes5").to("cuda")
pipe(prompt, guidance_scale=7.5, guidance_rescale=0.7).images[0].save("out.jpg")

Related Models

Cite as

@misc{lin2023common,
      title={Common Diffusion Noise Schedules and Sample Steps are Flawed}, 
      author={Shanchuan Lin and Bingchen Liu and Jiashi Li and Xiao Yang},
      year={2023},
      eprint={2305.08891},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}