Instructions to use stabilityai/sd-vae-ft-mse with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use stabilityai/sd-vae-ft-mse with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stabilityai/sd-vae-ft-mse", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
How to finetune my own VAE based on this model?
#9
by DJCan - opened
Any advice about settings about learning rate and so on?
Hi @DJCan , I'm looking for training code, can you point me to the repo pls?
I am doing the same thing! have you found the repo about training code?