Instructions to use TkskKurumi/KurumiMix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use TkskKurumi/KurumiMix with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("TkskKurumi/KurumiMix", 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
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
KurumiMix
Composition
unet weights
The model weights are interpolated with same composition in all UNet blocks.
| Model | Contribution |
|---|---|
| PastelMix | 40% |
| Counterfeit V2.5 | 20% |
| Counterfeit V2.2 | 20% |
| EimisAnimeDiffusion | 10% |
| BasilMix | 5% |
| AbyssOrangeMix2 | 5% |
vae weights
Pastel mix's vae is colorful and beautiful, but a bit over-saturated in my view. Mix a little bit other vae.
| Model | Contribution |
|---|---|
| orangemix.vae.pt | 10% |
| pastel-waifu-diffusion.vae.pt | 90% |
samples
- Downloads last month
- 8



