<h3 id="3d-artstyle-lora-is-on-noobai-xl-v-pred-now!">3D ARTSTYLE LORA is on NoobAI-XL V-pred now!</h3>For NoobAI-XL Epsilon / Illustrious 3D ART LORA visit this <a target="_blank" rel="ugc" href="https://civarchive.com/models/1015498/3d-art-style-noobai-xl-epsilon-v10-and-11">page</a>.LoRA specializes in creating artistic 3D images by adding lighting effects and knows a lot of characters.Recommended model for this LoRA - <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294/noobai-xl-nai-xl">NoobAI-XL V-pred 1.0</a>.If you can't use rescaling CFG features better use my 3D art lora for Epsilon.<h3 id="version-3-is-released!">VERSION 3 IS RELEASED!</h3><ol><li>Replaced about 40% of dataset for better quality images;</li><li>More effects, more characters, more stable 3D style.</li><li>Added also furries and traps.</li><li>Better 3D backgrounds. Now it is not so blurry as in previous versions!</li><li>Don't forget to enable rescale CFG! New versions is brighter!</li></ol><h3 id="version-2-is-released!">VERSION 2 IS RELEASED!</h3>What's new:<ol><li>Replaced about 50% of dataset for better quality images;</li><li>More effects, more characters, more stable 3D style!</li><li>Now optimized for vanilla <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294/noobai-xl-nai-xl">NoobAI-XL V-pred</a> 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.</li></ol>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).<h3 id="noobai-xl-tags:">NoobAI-XL tags:</h3><h3 id="for-version-3:">For version 3:</h3>3d, realistic (For Resident Evil, The Witcher, Mass effect, etc. r34 3D).OR3d, 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 facesidelighting, backlighting, underlighting, bloom, shadow, light paricles, sunlight, light rays, moonlightFor good background:<h3 id="for-version-2:">For version 2:</h3>3d \(realistic\)Optional:shiny skin, wet, oiled, shiny clothes, shiny facesidelighting, backlighting, underlighting, bloom, shadow, light paricles, sunlight, light rays, moonlightNo special negative.<h3 id="for-version-1:">For version 1:</h3>Main tags:3doptional:shiny skin, wet, oiled, shiny clothessidelighting, backlighting, underlighting, bloom, shadow, light paricles, sunlight, light rays, moonlighthelping tags:photorealisticnegative prompt:flat color, painting \(medium\), painterly, 2d, film grainTo 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: <a target="_blank" rel="ugc" href="https://danbooru.donmai.us/">https://danbooru.donmai.us/</a>My preview can help.<h3 id="noobai-xl-3d-quality-settings:">NoobAI-XL 3D quality settings:</h3>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 <a target="_blank" rel="ugc" href="https://civarchive.com/articles/10226/noobai-xl-10-v-pred-optimal-settings-and-loras-announcement">guide</a> 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 <a target="_blank" rel="ugc" href="https://openmodeldb.info/models/2x-DAT-2">DAT 2 x2</a> (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!<a target="_blank" rel="ugc" href="https://tensor.art/u/604375505701151021">https://tensor.art/u/604375505701151021</a>

3D ART LoRA (NoobAI-XL V-PRED) Realistic/cartoon (V3 update!)

What's new:<ol><li>Replaced about 50% of dataset for better quality images;</li><li>More effects, more characters, more stable 3D style!</li><li>Now optimized for vanilla <a target="_blank" rel="ugc" href="https://civitai.com/models/833294/noobai-xl-nai-xl">NoobAI-XL V-pred</a> 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.</li></ol>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).

Files with SHA256: de45798ebdcefc0f7321daced4b1a24303874028cbf951dd891cb96a959f4532