This LoRA aims to reproduce a drawn style, featuring loose, sketch-like lines. At higher strength, it creates a raw, scribbled look; at lower levels, it adds an organic, artistic touch by embracing line imperfections. Trained mostly on quick sketches over white backgrounds, it also adapts beautifully to colored illustrations. Experiment with its strength to discover unexpected results. I hope you'll enjoy to play with it.
I created THIS DISCORD SERVER to propose future models, keep you updated on upcoming training, gather your feedback, and facilitate member exchanges. A brief introduction will be required to unlock access to the appropriate channels.
If you like this LoRA, don"t hesitate to:
publishing your photos directly in the model's gallery.
support me by giving some BUZZ (to train next models)
visit my Tensor account to try most of my models.
Thank you to everyone who supports me !
Description
I remade the dataset.
This is my first try for a Krea2 style, it can be a bit improved on the lighter lines in my opinion. But hey, it works!
FAQ
Comments (1)
Fantastic LoRA.
Sometimes it fails to work at lower strengths, have to go up to 3 or 4. But the renders are high quality.
Great job on this one. Thanks for creating and sharing!