taesd3

madebyollin/taesd3

taesd3 is a machine learning model from madebyollin. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for diffusers. The card lists the license as mit.

TAESD3 is very tiny autoencoder which uses the same "latent API" as Stable Diffusion 3's VAE. TAESD3 is useful for real-time previewing of the SD3 generation process.

Downloads · 30 days

347

3% of all-time downloads

All-time downloads

11.1K

Public

Parameters

2.5M

19.7 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin9.9 MB · 50%

At a glance

Library: diffusers
License: mit
Access: Public
Created: Jun 14, 2024
Updated: Jun 14, 2024
SHA: d58dcacc

Spaces

Model card

From the Hugging Face model README

🍰 Tiny AutoEncoder for Stable Diffusion 3

TAESD3 is very tiny autoencoder which uses the same "latent API" as Stable Diffusion 3's VAE. TAESD3 is useful for real-time previewing of the SD3 generation process.

This repo contains .safetensors versions of the TAESD3 weights.

Using in 🧨 diffusers

import torch
from diffusers import StableDiffusion3Pipeline, AutoencoderTiny

pipe = StableDiffusion3Pipeline.from_pretrained(
    "stabilityai/stable-diffusion-3-medium-diffusers", torch_dtype=torch.float16
)
pipe.vae = AutoencoderTiny.from_pretrained("madebyollin/taesd3", torch_dtype=torch.float16)
pipe.vae.config.shift_factor = 0.0
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.png")

Library: diffusers
License: mit
Created: Jun 14, 2024
Updated: Jun 14, 2024