---
license: mit
---

# 🍰 Tiny AutoEncoder for Stable Diffusion X4 Upscaler

[`taesd-x4-upscaler`](https://github.com/madebyollin/taesd) is very tiny autoencoder which uses the same "latent API" as [`stable-diffusion-x4-upscaler`](https://huggingface.co/stabilityai/stable-diffusion-x4-upscaler)'s VAE.
`taesd-x4-upscaler` is useful for [real-time previewing](https://twitter.com/madebyollin/status/1679356448655163394) of the upsampling process.

This repo contains `.safetensors` versions of the `taesd-x4-upscaler` weights.

## Using in 🧨 diffusers

```python
import requests
from PIL import Image
from io import BytesIO

url = "https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/sd2-upscale/low_res_cat.png"
low_res_img = Image.open(BytesIO(requests.get(url).content)).convert("RGB").resize((128, 128))

import torch
from diffusers import StableDiffusionUpscalePipeline, AutoencoderTiny

pipe = StableDiffusionUpscalePipeline.from_pretrained("stabilityai/stable-diffusion-x4-upscaler", torch_dtype=torch.float16)
pipe.vae = AutoencoderTiny.from_pretrained("madebyollin/taesd-x4-upscaler", torch_dtype=torch.float16)
pipe = pipe.to("cuda")

image = pipe("a white cat", image=low_res_img, num_inference_steps=25).images[0]
image.save("upsampled.png")
```