Instructions to use SG161222/Realistic_Vision_V3.0_VAE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SG161222/Realistic_Vision_V3.0_VAE with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("SG161222/Realistic_Vision_V3.0_VAE", 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
- Local Apps Settings
- Draw Things
- DiffusionBee
How do I train with this model?
#10
by Ardeact - opened
I'm experienced in training models using the Stable Diffusion model, but with this model, I cannot get decent results. I've set the embedding training to render every 20 images, and every consecutive render looks worse than the other; Solid color, creepy dudes with white-powered faces. I ensured my training data works with Stable Diffusion and it does. Are there any parameters I should use? Or maybe a different cross-platform optimizer?
Ryan, i cannot answer your question BUT could you tell me how do you train a model?
do you have a blog, a website i could look at ?