Instructions to use ChenDY/NitroFusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ChenDY/NitroFusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ChenDY/NitroFusion", 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
ControlNets
#1
by oguzhanercan - opened
Hi, thanks for your work, model looks really good, tested it and text - generation alignment looks good. Are you planning to train controlnet and loras for this model?
Thanks for your appreciation. We do plan to train ControlNet to adapt to our models and the shifted scheduler.
@ChenDY How about a LoRA extraction? This is the most convenient way to use other SDXL distillations such as DMD-2 or Lightning with any checkpoint. Would love to see how NitroFusion fares.