Instructions to use Clybius/FLUX.1-Krea-dev-scaled-fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Clybius/FLUX.1-Krea-dev-scaled-fp8 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Clybius/FLUX.1-Krea-dev-scaled-fp8", 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
merge option flux
#1
by kalle07 - opened
hey ...
do you can merge kontext and krea model maybe in in 3 different weights ?
It's likely better/more flexible to extract Krea from Dev as a LoRA and apply it to Kontext for such things.
I'll be uploading a new quant of Flux Dev and Dev Krea soon using a new novel method (TPEC-Quant) for accuracy.