Type | |
Stats | 10,253 419,642 |
Reviews | (1,004) |
Published | Nov 26, 2023 |
Base Model | |
Trigger Words | modisn disney modisn disney style |
Hash | AutoV2 D803B444ED |
This is a merge model out of my own and RealCartoonXL by 7whitefire7
It kind of looks like a RealCartoonXL-Pixar XL, which does not exist as of writing this.
The trigger tokens are either "modisn disney" or "modisn disney style". They are not entirely necessary but recommended.
Clip Skip is not required, but maybe it creates better results in some cases.
Img2img aka "Disneyfication":
Choose any image you want (realistic photos of people work best)
Resize your image so that its resolution fits within SDXL resolution bounds (e.g. resize to 1024px on the shorter side)
Use AUTO1111 img2img tab and load image (or the equivalent for any alternative UI)
Choose Euler sampler (usually best results), start with denoising 0.1, steps 40-120 (lower denoising needs higher steps to compensate)
Enter "modisn disney style" as a prompt (sometimes giving a general description of the image can help, e.g. "modisn disney style, girl holding a cat"). You can try working with the negative prompt but keep both prompts short
Hit generate and see what you get! Play around with the settings, higher denoising values allow for stronger Disney render effect but will also deviate more strongly from the original image. CFG also controls the strength of the effect.
(Optional) Choose AUTO1111 loopback script on the bottom, I recommend staying with only 2 loops, start with the first loop at 0.1 and the second at 0.15 or 0.2, and see what you can do from there. It will allow you to use higher denoising values while suppressing unwanted "mutations" in the image.
This is not an inpainting model so inpainting will generally look terrible.