AiPlaygroundWM

In the middle of creating variety version of power girl with Stable diffusion WebUI. ? Old version Muscular version ?? Normal(?) version I wanna her to be a baby girl and make unrealistic. So add prompt " (floating:1.4) " And~ She flew away to the universe. Every image has exif info

 Sunday, I'm still playing with power girl Lora. Making variety version of power girl. In the middle of mature lady version  That left hand....challenging me! Challenge accepted!!!!!!!! First t2t, hires 2.5 , using variation seed. Didn't show up similar base image.  It's a Stable diffusion issue.  (Same setting,seed didn't work) Changing plan, trying to i2i upscale 1.5x three times, denoising strenth 0.3 Inpaint face. (Usually face inpaint is last process, why this time? Just mistake, lol) Googling for reference hand. Select and cut out hand. Remove origianl left hand Edit left hand color and out line Add the origianl Now i2i inpaint hand run!! Many time I tried but mostly that left pointer finger didn't reconized stable diffusion. So I just duplicate ring finger, make little finger. Ok ready to run Run~! Glove color didn't match. Saturation and lightness edit again Run again Make detail right hand. Run right hand Hm....color still doesn't match edit again R...

 Still playing with power girl lora I initially combined three different versions of Lora using dynamic prompts. However, due to the significant variations in their body shapes, I decided to stick with just one version.  power girl   As I continued, I felt a desire to experiment with a different version of  pantyhose  lora. Start a test to see how Lora affects. using XYZ plot, Prompt S/R begining weight is 0.8 Overly strong to influence style. And it's not tan color.  lower weight 0.7 Pantyhose color is uncertain, but batter than 1st test. Try again Boots color is more correct than without pantyhose lora.  But pantyhose color is still not tan. How about weight 0.75? This pantyhose lora for realistic but turn image to anime style. lol And It makes more correct boots color. I don't know Stable diffusion more and more. weight 0.73 This time, affected background badly and didn't work prompt 'looking back' weight 0.7 again Prompt works ' kneel ', ...

 Final result in 15 steps. MH V1 It's semirealstic but the result looks 90% real. Skin and pantyhose texture edited with photoshop 2592 * 3240 Cropped. Cowboy shot Close up If texture could be more realistic, I'm 100% happy!  Now I'm 95% satisfied.

Playing with stable diffusion WebUI, 3 different version of Power girl Lora https://civitai.com/models/189428/power-girl-dc-comics-lora https://civitai.com/models/300420/powergirl-nsfwsfw-dc https://civitai.com/models/170256/power-girl-cartoon-character-tier-03-patreon-request-or-superhero-or-ownwaifu prompt :  (full body:1.2) photo of power_girl, girl, solo focus, blonde hair, red (cape),  cleavage_cutout, (white_leotard), long sleeve, (blue_gloves), red_belt, (blue_boots), muscular, curvy body, huge breasts, abs, thick thighs,  __pose__, {__WAKA/background__|night city, neon lights},  (realistic, best quality:1.2), QuickHands, <lora:QuickHandV2:0.6> {<lora:CARTOON_DC_powergirl_ownwaifu:0.9>|<lora:powergirl:0.8>|<lora:powergirl-nvwls-v1:0.9>} (The weights are adjusted at each checkpoint) "Power!!" girl ?????? ???????????????????????? ......?? (Those results are random selecting) The three Lora that i use, quality has not much differences...