import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("saud-unboxai/ldm-vqvae", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]VQ-VAE for Super Resolution
This repository contains a pre-trained VQ-VAE (Vector Quantized Variational Autoencoder) model derived from the CompVis/ldm-super-resolution-4x-openimages model.
Model Overview
The VQ-VAE is a generative model that learns a latent representation of images by encoding them into discrete codes.
- Downloads last month
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support