3D ARTSTYLE LORA is on NoobAI-XL V-pred now!
For NoobAI-XL Epsilon / Illustrious 3D ART LORA visit this page.
LoRA specializes in creating artistic 3D images by adding lighting effects and knows a lot of characters.
Recommended model for this LoRA - NoobAI-XL V-pred 1.0.
If you can't use rescaling CFG features better use my 3D art lora for Epsilon.
VERSION 3 IS RELEASED!
Replaced about 40% of dataset for better quality images;
More effects, more characters, more stable 3D style.
Added also furries and traps.
Better 3D backgrounds. Now it is not so blurry as in previous versions!
Don't forget to enable rescale CFG! New versions is brighter!
VERSION 2 IS RELEASED!
What's new:
Replaced about 50% of dataset for better quality images;
More effects, more characters, more stable 3D style!
Now optimized for vanilla NoobAI-XL V-pred because Cyberfix V-pred models are not so good as Cyberfix NoobAI Epsilon models (CyberrealismXL has epsilon-prediction while NoobAI-XL V-pred has v-prediction). So I noticed that Cyberfix makes my pictures more like 2.5D photo than 3D.
I don't recommend for this LoRA Cyberfix versions anymore. Use pure NoobAI-XL V-pred 1.0 (Everything will be fine with anatomy, my dataset is big enough for good anatomy).
NoobAI-XL tags:
For version 3:
3d, realistic (For Resident Evil, The Witcher, Mass effect, etc. r34 3D).
OR
3d, cartoonish (For Overwatch, Fortnite, WoW r34 3D).
Tip: BTW YOU CAN USE realistic with OW, WoW and other cartoon characters! These tags are not strict. You will feel more effect from difference of realistic / cartoonish on original characters.
Optional:
shiny skin, wet, oiled, shiny clothes, shiny face
sidelighting, backlighting, underlighting, bloom, shadow, light paricles, sunlight, light rays, moonlight
For good background:
For version 2:
3d \(realistic\)
Optional:
shiny skin, wet, oiled, shiny clothes, shiny face
sidelighting, backlighting, underlighting, bloom, shadow, light paricles, sunlight, light rays, moonlight
No special negative.
For version 1:
Main tags:
3d
optional:
shiny skin, wet, oiled, shiny clothes
sidelighting, backlighting, underlighting, bloom, shadow, light paricles, sunlight, light rays, moonlight
helping tags:
photorealistic
negative prompt:
flat color, painting \(medium\), painterly, 2d, film grain
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:
Put "masterpiece, best quality" in positive and put "worst aesthetic, worst quality, low quality, bad quality, lowres, extra digits" in negative.
Recommended generation settings:
Euler A SGM Uniform (Also you can try Uniform, Simple, Normal, DDIM, beta schedulers but I prefer SGM).
30 steps, CFG 5-6.
Rescale CFG 0.4 - 0.7 (Or other rescaling features. Use my guide abot V-pred if your pictures are oversaturated).
CFG++ samplers are not recommended this time. According to my test it harms 3D volumetricity. Better use Euler A and rescale CFG For V-pred.
Highres fix:
0.25-0.3 denoising strength, 12-15 hires steps,
Upscalers: Foolhardy Remacri 4x or DAT 2 x2 (VERY powerful but slow. His main advantage - saving many small details. It is not so critical for anime but very critical for realistic 3D).
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!
Description
New in V3:
New pictures for better backgrounds and furries;
More volumetric than V2.
Price: Brighter. So don't forget to use rescale CFG.
FAQ
Comments (11)
Amazing, you alaways great!
What program do you use to create models? I want to create original Taimanin characters.
I use lora easy training scripts for making loras. It is available on github. To train SDXL loras you need at least 12 gb VRAM (not RAM).
@Enigmata Well, actually, you can train a LoRA on 6Gb or 8Gb VRAM, but it will be much slower process. 12Gb VRAM is just a "minimum" for your own comfort.
@Enigmata The steps are very complicated and the levels are very long. Creating LoRa with PixaiArt was easier for me than with other programs, in my opinion, like GitHub. Other similar programs are more complex, in addition to having many steps. PixaiArt is easy for me; you just import photos and that's it. Of course, you have to do some testing to get the model right, although obviously it's not high quality, but at least I already have my first character, Taimani, which I've already published. Cerastes (Taimanin)
i tested this lora and its not the best out there there is way more better ones but i dont know why this take that match of attention really
Not sure :3 Btw you can try my NoobAI Epsilon version or Illustrious version because V-pred version is for advanced users who can use rescale CFG on local webui or tensorart comfyUI workflow (where rescale cfg node is supported). Eps / IL versions are better if you use site generator.
anyways just telling you dont be offensive
you just proved me a lot of points