---
title: sd2.1-base-zsnr-laionaes6-perceptual
canonical_url: "https://www.modelscope.cn/models/bytedance-community/sd2.1-base-zsnr-laionaes6-perceptual"
md_url: "https://www.modelscope.cn/models/bytedance-community/sd2.1-base-zsnr-laionaes6-perceptual.md"
repository: bytedance-community/sd2.1-base-zsnr-laionaes6-perceptual
last_updated: 2026-06-05
license: openrail++
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
library_name:
  - lora
  - pytorch
frameworks:
  - pytorch
downloads: 4
stars: 0
tags:
  - stable-diffusion
  - text-to-image
---

# sd2.1-base-zsnr-laionaes6-perceptual

> sd2.1-base-zsnr-laionaes6-perceptual - bytedance-community 在 ModelScope 开源的模型。SD v2.1-base with Self-Perceptual Objective

bytedance-community/sd2.1-base-zsnr-laionaes6-perceptual 是 ModelScope 魔搭社区上的text-to-image-synthesis模型，采用 openrail++ 许可。

- **Repository**: bytedance-community/sd2.1-base-zsnr-laionaes6-perceptual
- **License**: openrail++
- **Tasks**: text-to-image-synthesis
- **Tags**: stable-diffusion, text-to-image
- **Downloads**: 4
- **Stars**: 0
- **Last updated**: 2026-06-05

Source: https://www.modelscope.cn/models/bytedance-community/sd2.1-base-zsnr-laionaes6-perceptual

---

# SD v2.1-base with Self-Perceptual Objective

This is the official model in [Diffusion Model with Perceptual Loss](https://arxiv.org/abs/2401.00110) paper.

This model is trained using the self-perceptual objective. It no longer needs classifier-free guidance to produce sensible images.

This model is trained using zero terminal SNR schedule following [Common Diffusion Noise Schedules and Sample Steps are Flawed](https://arxiv.org/abs/2305.08891) paper on LAION aesthetic 6+ data.

This model is finetuned from [stabilityai/stable-diffusion-2-1-base](https://huggingface.co/stabilityai/stable-diffusion-2-1-base).

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

## Usage

```python
from diffusers import StableDiffusionPipeline
prompt = "A young girl smiling"
pipe = StableDiffusionPipeline.from_pretrained("ByteDance/sd2.1-base-zsnr-laionaes6-perceptual").to("cuda")
pipe(prompt, guidance_scale=0).images[0].save("out.jpg") # No need for CFG!
```

## Related Models

* [bytedance/sd2.1-base-zsnr-laionaes5](https://huggingface.co/ByteDance/sd2.1-base-zsnr-laionaes5)
* [bytedance/sd2.1-base-zsnr-laionaes6](https://huggingface.co/ByteDance/sd2.1-base-zsnr-laionaes6)
* [bytedance/sd2.1-base-zsnr-laionaes6-perceptual](https://huggingface.co/ByteDance/sd2.1-base-zsnr-laionaes6-perceptual)


## Cite as
```
@misc{lin2024diffusion,
      title={Diffusion Model with Perceptual Loss}, 
      author={Shanchuan Lin and Xiao Yang},
      year={2024},
      eprint={2401.00110},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

@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}
}
```