Instructions to use gokaygokay/Fuse-it-Kontext-Dev-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use gokaygokay/Fuse-it-Kontext-Dev-LoRA 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("gokaygokay/Fuse-it-Kontext-Dev-LoRA") prompt = "Fuse this image into background" 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
Difference between this and Light-Fix-Kontext-Dev-LoRA
#1
by b1n0ry - opened
Hey,
what exactly is the difference between these two LoRA's?
Both use the same trigger text. Does one match the style and the other the lighting?
Can we use both LoRA's together at once to have the best possible integration of objects?
Thanks in advance
Hello, this one fuses the pasted object to background with the correct style. Light fix is normalizing the light for every object especially if an object is a lot darker or lighter than the scene, it matches the original light of the background