Instructions to use wikeeyang/Flux2-Klein-9B-True-V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use wikeeyang/Flux2-Klein-9B-True-V1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("wikeeyang/Flux2-Klein-9B-True-V1", 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
Can this Finetune be extracted as a LoRA?
#4
by Latentiq - opened
I really loved using this model. In my experience V1 has amazing adherence when using multiple references however I would really like to be able to use the Flux klein 9B and control the influence that this model has using the Lora Alpha and the ability to combine the lora with different base model quants like the new Int8 ConvRot.
Do you know if this would be possible?
May be, you can try some LoRA extract tool to test it.
Thank you! do you know if it has to be extracted as a difference from Base or regular Klein 9B? Appreciate your help!
The klein turbo lora had extracted from Klein 9B and Base.