Instructions to use Norod78/Flux_1_Dev_LoRA_Paper-Cutout-Style with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Norod78/Flux_1_Dev_LoRA_Paper-Cutout-Style with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Norod78/Flux_1_Dev_LoRA_Paper-Cutout-Style") prompt = "The cookie monster, Paper Cutout Style" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Number of images in training dataset
#1
by Viewegger - opened
Hello,
thank you for making this public! May I ask you how many images were used during Lora training?
Thank you! Only 14 image to get this quality is fantastic, flux is very promising indeed!
Viewegger changed discussion status to closed
