Sign In

JAV Riho_Shishido (宍戸里帆)

22
299
1
Updated: May 29, 2024
celebritysexyjavidolwomanjapanese
Verified:
SafeTensor
Type
LoRA
Stats
299
0
Reviews
Published
May 29, 2024
Base Model
SD 1.5
Training
Steps: 2,880
Epochs: 12
Usage Tips
Clip Skip: 1
Strength: 0.8
Trigger Words
rihoshishido_jav
breasts
short hair
brown hair
parted lips
pink lipstick
blush
Hash
AutoV2
037ACF1E41
Created on Civitai

Imitation model. Modelled after young Japanese AV actress Riho Shishido (宍戸里帆).

Riho is probably one of the first gen-Z JAV actress that I trained on, having only turned 23 years old this year. Famed for her G-cup, and self-proclaimed "puffy nipples" that somehow turned in favour of her personal branding, Riho's activity in the industry ramped up significantly on the 2nd half of 2022. I always like to appraise JAV actresses based on their unique recognisable features, so for me, its' Riho's fairly chubby look, petite body and girl-next-door personality. Would that be something that would spice up your SD journey?

~~~~~~~~~~~~~~~~~~~~~~~~~~
Recommended LoRA strength: 0.8 (0.6-1.0 are plausible range dependent on checkpoints; higher values >1 increases aging..)

Main Prompt:

rihoshishido_jav, breasts, short hair, brown hair, parted lips, pink lipstick, blush

variations: bob cut, wet hair

facial variations: parted lips, pink lipstick, makeup, teeth, smile, grin

*Use of facial prompts depend on checkpoints, you can make a case for using it or not - personal preference

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Checkpoints thatworks well

1) Realisian.

Stellar performance overall. only issue is that it doesnt model her "mole below eye" very well.

2) RealisticMix

Works OK. correct height, good body proportions, just alittle off with facial resemblance.

3) PerfectWorld

Leaning towards 2.5D.

~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Note for achieving good resemblance:

Relatively straightforward to use. If you are lazy, you can just use the main prompt to control for everything and apply Adetailer to fix the faces.

Else, you can separate the prompts into 2 stages.

1. Generate the main prompt using a LoRA strength of 0.8-1.0. so its probably safe to say that this weight is stable for use.

2. Now depending on what you use for (1), turn on facial Adetailer, and put something like

"face of rihoshishido_jav, short hair, brown hair, parted lips, lipstick, <lora here>"

For Adetailer strength, you can try 0.40 for close-up or cowboy shots, and even 0.45 for full body ones.

It is still better to use AD at baseline generation (512,768 etc) and then upscale it later.

Recommended approach: is to not use HiRes, but upscale it with img2img instead.

Use a denoise strength of 0.20 -0.25 (anything higher will overcorrect face during the process), and turn off Adetailer. Even 0.3 is fine.

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Issues:

No issues so far, apart from some badHands (in some checkpoints).

Post-production edits/Reproducibility:

No edits. all img2img original upscales.

Happy prompting. And do share [SFW] creations~