Instructions to use lodestones/Kromoss with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lodestones/Kromoss with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("lodestones/Kromoss", 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
Kromoss rocks
#12
by Shiza001 - opened
Kromoss definitely rocks, but only for realism and photorealistic stuff for now. For anime, I'm getting a lot of nonsense speech bubbles everywhere and anatomy errors (even with negative prompts specified). I don't know if this is the last version of this model, because there is still some room for improvement (edit: the model is still in development, sorry for my dumb thought π
). I can see that kromoss definitely have the potential to be the new chroma :)
Shiza001 changed discussion title from Kromoss rocks, but... to Kromoss rocks