Instructions to use Jersonm89/Avatar with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Jersonm89/Avatar with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Jersonm89/Avatar", 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
there is a typo in one of the promts
#1
by fcakyon - opened
Did you really train with only a few angles as https://t.co/Wd1yMZdP1Q? The quality is amazing!
Promts should be Johnny Depp instead of Will Smith here:
https://huggingface.co/Jersonm89/Avatar#sample-images-johnny-depp---prompt-portrait-will-smith-maleavatar-style
Yes, I trained it with that dataset at 4000 --max_train_steps I think it could be done better, I'm currently with one of the Simpsons who is giving me gray hair.
Is there a way to use this with one of our own trained models so that we can turn ourself into 1 of these?