Instructions to use Thytu/FLUX.1-Kontext-dev-cage-ify with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Thytu/FLUX.1-Kontext-dev-cage-ify with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-Kontext-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Thytu/FLUX.1-Kontext-dev-cage-ify") prompt = "Replace the face with Nicolas Cage's face" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
training process
#1
by Donzo0 - opened
Could you go more into details on the training process https://huggingface.co/Thytu/FLUX.1-Kontext-dev-cage-ify#training-process
I also used fal ai to train, the generations did not match the character used in the lora.