FOR NOOBAI-XL V-PRED / V-pred cyberfix USE THIS LORA if you can use rescale CFG option (local webui forge, comfyUI, Comfy on Tensorart). For other cases (site generators, favorite NAI Eps / Illustrious mixes) use this lora.
V4 IS AVAILABLE!
What's new:
Replaced about 50% of dataset for better quality images;
More effects, more characters, more stable 3D style;
Added activation tag.
BEST MODELS TO USE 3D LORA:
NoobAICyberfix1.1 perpendicular
NoobAI-XL Epsilon (v. 0.75, v 1.0 or 1.1)
LoRA was trained on NAI Epsilon 0.75 because loras from 1.0 are oversaturated and loras from 1.1 have worse style but you can easily use this lora on 1.1 checkpoint (including cyberfix 1.1).
Please don't use it on anime mixes because they kill 3D style!
If you
NoobAI-XL / IL tags:
Main tag:
FOR VERSION 4 and Illustrious 0.1:
3d, realistic (For Resident Evil, The Witcher, Mass effect, etc. r34 3D).
OR
3d, cartoonish (For Overwatch, Fortnite, WoW r34 3D).
FOR VERSION 3: 3d \(realistic\)
FOR VERSIONS 1 - 2: 3d
Body effects and tags:
shiny skin, wet, oiled, toned, curvy, plump, muscular, tan, tanlines, cellulite
sidelighting, backlighting, underlighting, bloom, shadow, light paricles, sunlight, dappled sunlight, light rays, moonlight
FOR V1, V1.1:
To prompt known franchise characters use prompt order: {character name}, {francise name}, other tags.
FOR NEWER VERSIONS:
DON'T NEED FRANCHISE TAG. BETTER DON'T USE IT.
All characters in my LoRA are tagged with danbooru tags! So use tags from this site: https://danbooru.donmai.us/
My preview (from all versions) can help.
NoobAI-XL 3D quality settings:
Put "masterpiece, good quality, 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. Personally for NAI Epsilon Euler is better than Euler A while on NAI V-pred euler A is better.
30 steps, CFG 5-6.
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
NoobAI-XL Epsilon 075 (Very good with NoobAI-Xl Epsilon 1.1 Cyberfix).
FAQ
Comments (9)
Will there be an Anima version? Because it's really good!!!
Yes, I have some test versions for Anima and I am planning to upload it too :3
@Enigmata YES! It's because he's an amazing Lora and he's accomplished great things, and I'm curious how this incredible Lora would fare with Amina (*/ω＼*)
Anima version - https://civitai.red/models/2663198/
Curious question is it normal for the lora to add what looks like a coffee holding or making device? Do I have to put coffee in my negative?! Lol
omg idk, it depends on prompt :3 I dodn't see any coffee without tags
@Enigmata I think i found the culprit lol, it was cause I had Blender in prompt was meant to be 3d_blender but somehow forgot the 3d part, great lora, works well for my female werewolves, and for me it works great with Hassaku model
@the_guilded_hero nice :3 Yes, lora has anthro/ furry in dataset too for better fur textures and other details.