Question about training data for Overlay-Kontext-Dev-LoRA

#7
by zhangjinyang - opened

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! πŸ™

Sign up or log in to comment