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
legend model
π 2
#9 opened about 23 hours ago
by
changev
BF16 + DMD/DMD2 gets crispy for me, but 50-step BF16 looks way better (Even longer)
#8 opened 1 day ago
by
uzumymwka
Kromoss roadmap: Next checkpoint, higher resolution training, and future improvements?
π 2
1
#7 opened 3 days ago
by
ToxicFate
w4a8 or w6a8 kromoss
#6 opened 7 days ago
by
lordkek
How does it differ from the fine tune the MOSS team released?
1
#5 opened 12 days ago
by
RogerBacon
Tried using the int8 version but it come out with error
π 1
2
#4 opened 13 days ago
by
leonvizard
excesive BLUR by defailt
π 2
8
#3 opened 14 days ago
by
Talanca
Demo for this model on Spaces
π 4
#2 opened 14 days ago
by
multimodalart