Instructions to use lvladikov/Krea2-Turbo-Distill-4step-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lvladikov/Krea2-Turbo-Distill-4step-LoRA with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("krea/Krea-2-Turbo", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("lvladikov/Krea2-Turbo-Distill-4step-LoRA") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Model Ranks
1
#13 opened 29 days ago
by
Goghor
[09 Sep 2026] - ๐ญ The follow up 2-step LoRA is now its own project (for the curious...)
๐ 1
#9 opened about 1 month ago
by
lvladikov
This is awesome!
3
#8 opened about 1 month ago
by
mikkoph
NOTE - Final Version of the 4-Step LoRA was released today (folders and files restructured, renamed and cleaned up)
โค๏ธ 7
1
#7 opened about 1 month ago
by
lvladikov
LoRA Strength Comparisons
๐ 2
3
#6 opened about 1 month ago
by
Goghor
This reminds me of the SDXL-era DMD2
๐ 1
1
#4 opened about 1 month ago
by
Goghor
Absolutely brilliant!
1
#3 opened about 1 month ago
by
Talanca
awesome work
๐ 2
2
#2 opened about 2 months ago
by
Salazarkzz
Demo for this model on Spaces
6
#1 opened about 2 months ago
by
multimodalart