Norman Rockwell style LoRA for Pony V6 XL and Illustrious-XL v0.1. For best results, prompt using Booru tags. See training data for image list, tags and training config.

Norman Rockwell Style

Most Common Bucket Sizes: 1088x1152 (x53), 896x1152 (x24), 960x1152 (x21). I used the same script for as "V6" to train "V12" on Animagine XL V3.1.

norman_rockwell_style_animagine3.1_v12.safetensors

Animagine XL V3.1

Illustrious-XL v0.1

(old) Illustrious-XL v0.1

Pony V6 XL

(old) Pony V6 XL

pony ver is here↓<a target="_blank" rel="noopener noreferrer nofollow" href="https://tensor.art/models/770828294963617818">https://tensor.art/models/770828294963617818</a>To better reproduce his style, make sure to add "norman rockwell style" in the positive prompt. Alternatively, you can try increasing the LoRA weight (1-2). If it has too much of an anime look, try adding "anime" in the negative prompt.If you want the output to look more like a painting, you can add "painting" in the positive prompt, however, you may need to add something like "canvas, picture frame, paint brush" to the negative prompt. Alternatively you could use another LoRA with a more bold brushstroke style to coax it to look more painterly and avoid the word ambiguity.

About this version
Most Common Bucket Sizes: 1088x1152 (x53), 896x1152 (x24), 960x1152 (x21).

I used the same script for as "V6" to train "V12" on Animagine XL V3.1.

Files with SHA256: 71fc70cfe890b7a3015035318f08e888d13b4552bdc5976bc6347ad1196f5975