Rude Frog 3D style is on NoobAI-XL V-pred now!

Recommended model for this LoRA:

For V-pred version: - NoobAI-XL V-pred 1.0. (Don't use cyberfix version for V-pred).

For Epsilon-pred version - NoobAI-XL Epsilon 1.1 , Cyberfix versions.

If you can't use rescaling CFG (in forge / ComfyUI) it is better to use my lora for Epsilon.

I. NoobAI-XL tags:

Main tags:

rudefrog3d, shiny skin

Optional:

large breasts, huge breasts, ???????, stomach

Some popular clothes from RF arts:

black choker, white choker, o-ring choker, shrug \(clothing\), bridal gauntlets, thigh boots, highleg panties, black panties, crop top

General aesthetic tags for NoobAI-XL:

Put "masterpiece, best quality, highres, absurdres, very awa" in positive and put "worst aesthetic, worst quality, low quality, bad quality, lowres, extra digits" in negative.

Tips:

To prompt known franchise characters use their names. Don't add franchise anime / game names! It can harm 3D style!

If franchise character has too agressive baked-in style you can put his franchise game / anime in negative and 3D will be applied!

All images in my LoRA are tagged with danbooru tags! So use tags from this site: https://danbooru.donmai.us/

My preview can help.

NoobAI-XL 3D quality settings:

Recommended generation settings:

Euler A SGM Uniform (Also you can try Uniform, Normal, beta schedulers but I prefer SGM), 30 steps.

CFG 4! (NOT MORE FOR BOTH VERSIONS).

For V-pred only: rescale CFG 0.5 (Or other rescaling features. Use my guide abot V-pred if your pictures are oversaturated on V-pred version).

CFG++ samplers are not recommended this time.

Highres fix:

0.25-0.3 denoising strength, 12-15 hires steps,

Upscalers: Foolhardy Remacri 4x (good and fast, very popular) or DAT 2 x2 (VERY powerful tile upscaler but slow. His main advantage - saving many small details).

Also you can try HAT-S SR 2x - it is not so fact as esrgan (foolhardy remacri) but not so slow as DAT and it's also good modern tile upscaler as DAT).

Adetailer:

Denoising strength 0.25 - 0.3. Detection model confident threshhold: 0.7-0.8.

Inpaint only masked padding pixels - 70-90 pix for face models, 156-256 for hands models.

Please don't forget to rate my LoRA. This motivates me to do more!

https://tensor.art/u/604375505701151021