madebyollin/taesdxl

🍰 Tiny AutoEncoder for Stable Diffusion (XL)

TAESDXL is very tiny autoencoder which uses the same "latent API" as SDXL-VAE. TAESDXL is useful for real-time previewing of the SDXL generation process.

Comparison on my laptop:

This repo contains .safetensors versions of the TAESDXL weights.

For SD1.x / SD2.x, use TAESD instead (the SD and SDXL VAEs are incompatible).

Using in 🧨 diffusers

import torch
from diffusers import DiffusionPipeline, AutoencoderTiny

pipe = DiffusionPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16
)
pipe.vae = AutoencoderTiny.from_pretrained("madebyollin/taesdxl", torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "slice of delicious New York-style berry cheesecake"
image = pipe(prompt, num_inference_steps=25).images[0]
image.save("cheesecake_sdxl.png")