Instructions to use gonzalu/YFG-SushiStyle with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use gonzalu/YFG-SushiStyle 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/stable-diffusion-3-medium", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("gonzalu/YFG-SushiStyle") prompt = "YFG-SushiStyle, A sly fox with Ferenc ears, entirely made of sushi, standing in an enchanted forest where everything is made of sushi." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Training
#1
by cyan2k - opened
Amazing Lora! The first time I had fun using SD3, haha
What training framework do you use, and do you mind sharing the training parameters?
Tried my self doing some experiments, but all resulted in broken models and dreams :(
Thanks!
Thank you... let me find the settings and share ... look for it in the files section
Thanks!
I would guess it's using the 'sd3-improvements' branch of OneTrainer?
Yes
gonzalu changed discussion status to closed