You can achieve either colored or monochrome results (exclude any color tags and use monochrome, greyscale, hatching \(texture\) ).<h3 id="artist's-resources:-d6ejnvyt9">Artist's resources:</h3><a target="_blank" rel="ugc" href="https://www.pixiv.net/en/users/4122">https://www.pixiv.net/en/users/4122</a><a target="_blank" rel="ugc" href="https://radiohead.fanbox.cc/">https://radiohead.fanbox.cc/</a><hr />If you found the LoRA interesting or somehow useful, consider supporting me by joining my <a target="_blank" rel="ugc" href="https://t.me/NortromDTS">Telegram channel</a>. I post thoughts there and do streams of LoRA making.<hr /><h1 id="best-shot-update:-owq22l9kb">Best shot update:</h1><hr />WotBRecommended samplers:<ul><li>DPM SDE++ ★ - 18 steps</li><li>DPM++ 2S a - 16-20 steps</li><li>DDPM - ~40 steps</li></ul>Recommended upscale settings - <a target="_blank" rel="ugc" href="https://imgur.com/joMSsME">here.</a>Recommended checkpoint:<a target="_blank" rel="ugc" href="https://civarchive.com/models/1201815/nai-xl-vpred10-2d-accelerated?modelVersionId=1412644">NAI-XL vpred1.0 2d accelerated "Final" version</a>Won't get any better or worse.<hr />ILLUSTRIOUS UPDATEWell who would've thought that making a good style lora of an artist who has little colored images and has no consistent coloring techniques is nearly impossible. I've spend 5 days trying to achieve good result but ended up unsatisfied again. Well, at least it is something.Illustrious version is really different from the pony one, and I don't know exactly why is that.Again, it would be great if you share your generated results and maybe leave a feedback.

RadioHead / Radio Paranoia Style Mimic | v-pred + Ill + Pony LoRA

NOOB version.Fixed dataset and new training settings.DISCLAIMER (applies only to NOOB-AI version): use my parameters to achieve best results. I didn't test the Lora on other checkpoints, so keep that in mind.Trained on <a target="_blank" rel="ugc" href="https://civitai.com/models/833294?modelVersionId=1190596">https://civitai.com/models/833294?modelVersionId=1190596</a>.Was tested on <a target="_blank" rel="ugc" href="https://civitai.com/models/1201815/nai-xl-vpred10-2d-accelerated">https://civitai.com/models/1201815/nai-xl-vpred10-2d-accelerated</a>, both "Final" and "style2" versions. Better CFG for "Final" is between 2.1-2.5, for "Style2" is 2.5-2.75. Recommended settings:20 steps Euler DY CFG++ + Align Your Step CFG 2.4Hiresfix settings:Use <a target="_blank" rel="ugc" href="https://huggingface.co/Akumetsu971/SD_Anime_Futuristic_Armor/blob/main/4x_fatal_Anime_500000_G.pth">Fatal Anime</a> upscaler if output is too bright or <a target="_blank" rel="ugc" href="https://huggingface.co/FacehugmanIII/4x_foolhardy_Remacri">Foolhardy</a> in other cases. Hires steps 12, denoise from 0.2 to 0.6, upscale by 1.5, sampling method Euler Dy.Enhance prompt string (put it after all your main prompt):masterpiece, best_quality, very_awa, absurdres, very_as2, hdr, High_dynamic_range, rich_details, clear_shadows_and_highlights, intense, enhanced_contrast, highly_detailed, amazing_quality, very_aestheticUse "detailed background" if necessary.

Files with SHA256: d306199b83a48ff3d6ae9ca30b2e8cd4a90f2bfa39725f4d7beb335330e845f8