Back for more JAV actresses!
Hazuki debuted in the industry under another alias (Mizuki Hayakawa), signed under the SOD label. SHe first gained traction and popularity, from signing up as a member of idol group called "原宿☆バンビーナ", whilst juggling her JAV schedule. From there the participation in Tokyo Idol Festival gave her reasonable coverage, spreading her fanbase. Eventually, she started with her current Hazuki alias in 2020. I would consider her a fairly versatile JAV actress, though her popularity seems to come mainly from her performance in femdom and ???? genres. Signature feature is her fairly thick (botox-like) lips, and bob cut.
variations: bob cut, wet hair
facial variations: parted lips, lipstick, makeup, teeth, smile, grin, mole below eye
*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) JuicyGirls
Works reasonably well. But facial expression is fairly pale.
3) RealisticMix
Similar to (2), but the over-exaggerated ?????? size can be abit hard to deal with.. sometimes.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
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 hazukiwakamiya_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. I prefer 0.2 since I use foolhardy-reMarci.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
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~
v1. Initial release. trained on 160+ images.
Epoch #12 chosen as the most stable epoch.
1. Os direitos dos modelos repostados pertencem aos criadores originais.
2. Criadores originais que desejam reivindicar seus modelos devem contatar a equipe do SeaArt AI pelos canais oficiais. Clique para reivindicar
