Hugging Face's logo

rdm0
/
autoencoderkl-sd0-init

Diffusers
Safetensors
Model card Files
xet
 Community
How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("rdm0/autoencoderkl-sd0-init", dtype=torch.bfloat16, device_map="cuda")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]

About this Model

This model copy weights from stabilityai/sd-vae-ft-ema, but with the last DownEncoderBlock2D and the first UpDecoderBlock2D removed. As a result, this model cannot be used without finetuning. The purpose is to obtain a VAE with a scale factor of 4.

Downloads last month
3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support