Downloads · 30 days
15.5K
2% of all-time downloads
taesd
madebyollin/taesd
taesd 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.
TAESD is very tiny autoencoder which uses the same "latent API" as Stable Diffusion's VAE. TAESD is useful for real-time previewing of the SD generation process.
All-time downloads
736K
Public
Parameters
2.4M
123 MB on disk
Likes
73
Public
Repo makeup
Click a slice to open those files.
.safetensors19.6 MB · 67%
At a glance
- Library
- diffusers
- License
- mit
- Access
- Public
- Created
- Jul 21, 2023
- Updated
- Nov 7, 2024
- SHA
- 614f7681
Model card
From the Hugging Face model README
🍰 Tiny AutoEncoder for Stable Diffusion
TAESD is very tiny autoencoder which uses the same "latent API" as Stable Diffusion's VAE. TAESD is useful for real-time previewing of the SD generation process.
This repo contains .safetensors versions of the TAESD weights.
For SDXL, use TAESDXL 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-2-1-base", torch_dtype=torch.float16
)
pipe.vae = AutoencoderTiny.from_pretrained("madebyollin/taesd", torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "slice of delicious New York-style cheesecake topped with berries, mint, chocolate crumble"
image = pipe(prompt, num_inference_steps=50, generator=torch.Generator("cpu").manual_seed(0x7A35D)).images[0]
image.save("cheesecake.png")
- Library
- diffusers
- License
- mit
- Created
- Jul 21, 2023
- Updated
- Nov 7, 2024