AiPlaygroundWM

One of the result. Futuristic vampirella . Base (1.5x hires. 768 * 960) i2i uscale x2 x2 (3072 * 3840) Inpaint detail parts. Final edit detail, color, sharpen, contrast and etc. Every image has exif info

In the middle of generating veriety version of the vampirella. parameters (full body:1.2) photo of Vampirella, solo focus, look at viewer, very long hair, micro bikini, muscular, curvy, (huge breasts:1.35), abs, narrow_waist, huge pelvic, (thick thighs:1.35), high_heels, boots, (dynamic pose, fighting stance:1.2), blood_puddle, partially submerged, body half-submerged, (full moon), forest, Blood everywhere, (best quality, realistic) <lora:VampirellaV2:0.4> v4mp1r3ll4, <lora:angel_wings_v10:0.6> (angel_wings) Negative prompt: (breasts out, nude:1.4), extra hand, extra foot, close up, (multiple view), missing finger, extra fingers, fused fingers, cropped, (crossed eyes, worst quality,bad quality:1.4),monochrome, greyscale, (text, signature, watermark:1.4), mutated Steps: 15, Sampler: DPM++ 2M, Schedule type: Karras, CFG scale: 7, Seed: 1489340367, Size: 512x640, Model hash: b89ba7f884, Model: meichidarkV38_pruned, Denoising strength: 0.55, Clip skip: 2, This one As you can se...

 The evolutionary process of mankind ??? In the middle of the new lora test :  <lora:gewasc:0.7> This is about pantyhose lora. check point : meichidark v3.8 check point : camelia mix 2.5d v1 check point :  darksun  check point : MH mix v2 check point : coma hard check point : copaxtimeless v1 check point : astra anime v5b check point : samaritan v3 As you can see, it's shinny, tan color and realistic texture of detailed pantyhose are great! But this lora effected hair color and hair style, other clothes parts, limbs(body proportion, gesture), background.

 Pony doesn't work AD(after detailer). Even i2i inpaint neither. but today's check point is  realcartoonXL_v6   works AD! I was trying to testing AD settings. Use separate width/height. hm?  How about default settings again? Unchecked Use separate width/height. Still works!? Every image has exif info

 Check Point model :  protovisionXLHighFidelity3D 816 * 1024  Hires 1.5 Denoising strength : 0.45 Fairy tale , fantasy style, 1Girl,  a human  embracing posing with a giantfusion of unicorn, Magical,  storybook style, enchanting, highly detailed, (realistic photograph, best quality, finely detailed, absurdres) negative prompt : mutated, extra arms, (worst quality, low quality, glitch, artistic error), (Watermark, Tex,signature), blurry, 15 40 Same as Stable diffusion 1.5. More steps not any guarantee better quality. (At least, in my settings) Changing check point model :  RealVisXL Changing prompt : (realistic photograph),  red and greenish color theme,  1Girl,  fashion model posing with a giantfusion of horse,  in nature,  enchanting, highly detailed, (best quality, finely detailed, absurdres) There is no detail both. That hexagon artifact, every surface.... check point :  realcartoonXL_v6 Same results. Hexagon ...

About 1 year ago I've tested denoising, and today test again.   New ram has arrived~ 8GB *2 ==> 32GB *2 upgrade! 15steps 512*640 (4:5 ratio) hires 2.5x Check Point model is :  AstrAnime 5b 0.4 0.5 0.55 0.6 Tiled diffusion extension off by mistake, but runs well!? Keep off and tested. [ The face all good because using AD(after detailer. faceand hands. denoising 0.55) ] 0.55 and 0.6 slightly different. and better than 0.4 certainly. Similar results. Change Check Point model : meichidark V3.8 ????? Same as before How about 0.7? ????Ok. Pretty mess up Remove 0.4 0.5 0.55 0.6 Denoising over 0.55 is better than I think. How about at steps 20 0.5 0.55  0.55 result's heels started wierd. How about with lora? 0.6 Ok definitely 0.6 is out. Conclusion : Denoising is under 0.55 Every image has exif info