Instructions to use heldn/palestine_flagFlux with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use heldn/palestine_flagFlux 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("heldn/palestine_flagFlux") prompt = "1boy, hold a flag palestine_flagFlux, <lora:palestine_flagFlux:1>, hyper detailed, anime, best quality" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Inquiries on dataset size
#1
by Jinyi-Resaro - opened
Hi Heldn! Great work on the lora! May I ask if you trained this with dreambooth lora? How many images have you used to train this? How many steps and what's the learning rate you used to train?