Instructions to use ilkerzgi/Overlay-Kontext-Dev-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ilkerzgi/Overlay-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("ilkerzgi/Overlay-Kontext-Dev-LoRA") prompt = "Place it" 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
Question about training data for Overlay-Kontext-Dev-LoRA
Hi @ilkerzgi ,
Thanks for sharing this great LoRA β the overlaying ability on top of FLUX Kontext is very impressive! I am currently experimenting with Kontext-based editing and image-to-image workflows, and your model is a very valuable reference.
I wanted to ask:
is the training data (or a subset/description) used for Overlay-Kontext-Dev-LoRA publicly available?
was it based on a curated dataset, synthetic pipeline, or proprietary images?
could you possibly share any information about the training data format.
Even a high-level description of the dataset or data construction process would be greatly helpful for research and experimentation.
Appreciate your work and thank you in advance! π