Instructions to use kontext-community/relighting-kontext-dev-lora-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use kontext-community/relighting-kontext-dev-lora-v3 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("kontext-community/relighting-kontext-dev-lora-v3") prompt = "Turn this cat into a dog" 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
- Draw Things
What is meant by "You should use `` to trigger the image generation." ?
I've never seen this before. What does this mean? There is no keyword or actually use those marks to activate the LORA?
how to use this lora
I've never seen this before. What does this mean? There is no keyword or actually use those marks to activate the LORA?
it's actually blank. No metadata. Most likely there is no trigger, simply enabling the LoRA in GUI is enough; is my assumption here.
this lora seems to mostly just tint the image. anyone got good results?
Maybe we can find the answer from the training dataset. https://huggingface.co/datasets/kontext-community/relighting
Maybe we can find the answer from the training dataset. https://huggingface.co/datasets/kontext-community/relighting
I randomly picked a picture and used the prompt words in the data set. The result is that as long as certain prompt words are used, there will be a relight effect. The difference between load and no load this lora is very small.