

I uploaded 120+ images all in sketched sepia style, some also with slight pastel accenting.
Trained with: DreamShaper v8 A "does it all" model by Lykon. Particularly good at art.
The uploaded set includes individual items, animals, scenery, fantastical. I used the same photo set for 2 LORAs. This one was my 2nd, trained on the DS8. (The other on Stable Diffusion 1.5).
It seems adding the terms “vintage. Sketch. Sepia. Pastel” or variances help the outcomes.
I tried and compared DS8 and a few others by themselves with the terms/modifiers/words: “vintage, sketch art, sepia, pastel” and then added this fine tuned model with and without the extra terms.
Results SEEM to come out better (or as I was seeking) w/model + terms added depending on desires. (I’m liking the results of adding both of my sketch fine tuned models even more).
I’m still testing and enjoying the outcomes. I invite you to have fun and experiment along with me.
We recommend using these trigger words when prompting Vintage Sketch DS8 to get the best results:
See what people have made with this model
No comments yet.

No comments yet