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("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("ostris/sdxl-sd1-vae-lora")

prompt = "photo in the sd1 latent space"
image = pipe(prompt).images[0]

SDXL SD1/2 VAE LoRA

This LoRA converts SDXL models to use the SD1/2 latent space. More info coming soon.

I recommend using this VAE with this LoRA sd-vae-ft-mse-original

Examples

Coming Soon

How to Use

Coming soon

Downloads last month
11
Inference Providers NEW
Examples

Model tree for ostris/sdxl-sd1-vae-lora

Adapter
(8378)
this model