Currently working on Rugged resolve Z image turbo, because I cant post images on here without the specific model I have to post test pictures on the last version of RRS. so I apologize if you download any of the sd1.5 models hoping for the same results. Maybe in a week or two I'll post V1 on civitai, currently it works very well but it is still ZIT and needs a good paragraph long prompt to get real results. Male anatomy wise its fantastic, soft core and solo stuff it works great on, basic nsfw it does good on. This will not be a hardcore porn model so if you were hope for extreme penetration shots or things of that nature im sorry but as the maker of this model that stuff doesn't really interest me. currently things im still working out are better bulges, more buff burly rugged hairy men, I would still love to get both a flaccid and erect option like noob-ai and flux can do with or without a foreskin if i cant there are a couple of wonderful loras for that already on civi. So far I have achieved basically burning out female/heterosexual content this model was distilled on meaning even if wanted a naked woman she will still have a set of testicles, still working on that whole frontal penetration like you would see on a m/f shot, so far its just alot of docking so if your into that YAY. I am doing to my best to achieve that same simple but effective prompting style of https://civarchive.com/models/681901/indigo-void-furry-fused-xl-furry-noobai which I absolutely love.
Description
Improved Picture quality
Simpler prompting for better results
Removed VAE so no more overlapping greyish tone when using img2img.
Not directly A NSFW model but should have improved results now for hot man on man action or nudity especially when using img2img without the overlapping greyish hue.
Somewhere along the lines the dicks became a little wonky but just need a img2img or two to fix up, will fix in 4.0.
If your like me and have a dead hamster on a wheel in the ol noodle I recommend the PA7 prompt generator, its a application that has a variety of camera styles, types of lights, physical attributes like face types, and various photo style of prompts to help bring full detail into your generations. https://civitai.com/models/308241/pa7promptgenerator
Because Fuck SDXL
FAQ
Comments (5)
"Removed VAE so no more overlapping greyish tone when using img2img."
Not quite sure this is entirely resolved in version 3.
Generating an image without VAE selected and then using Ultimate SD Upscale, still doubles the fade amount.
What works for me, is generating image without VAE and then adding VAE in img2img (or vice versa).
I'v noticed it still does that a little and I'll try and remove that in 4.0, im not to sure why it would be doing that even after removing the vae, it could just be the model itself. But I made a img using your prompts for the guy on the beach and I didnt notice it overly much even after a few img2img. I don't use Ultimate sd Upscale so im not sure how it effects the pictures I just DAXx4 and its never given me an issue. But thank you letting me know I appreciate the feed back
I'm a little late so maybe this was already figured out but models have various details that can be adjusted to change the general look and color tone of outputs. These adjustments are brightness, contrast, three color tones, and extra noise/detail. The grey look might be from the model having lower contrast or higher brightness than normal. It's not as simple as just tweaking those variables though, since every adjustment affects the images, and could lead to burnt or mangled gens.
You can find more info about it over here: https://github.com/hako-mikan/sd-webui-supermerger?tab=readme-ov-file#adjust
But the model still looks great to me, honestly, especially with the newer updates.
Still impressive. Thank you for the V3 Update.
I uploaded a little comparison, and all 3 Versions have wonderful "specialities".
V 1 is a little more "nsfw" but sometimes glitchi. Its for curiosity perfect.
V 2 is in terms for skintones / shadows a little more better than V1. And is a little better in intimate things.
V 3 is a little bit different than V1+2 it sometimes produces better portraits / face details. In lower Epochs ( < 1960s) it is posing differenter than the older Versions.
All 3 are very sensitive / touchy for sampler, scheduler, cfg and steps. V3 sometimes needs sometimes more cfg with Karras Scheduler and its sometimes not easy to find the right "weight" between Skintone and proper Composition.
Because: under / around CFG 4 (for my waifu prompting style) the skintones are very realistic. I can play with VAEs (Voidnoise, Tonerange and EMA560000 (perfect for tattoo and skindetails)) but the Sampler losses token attention. If i go CFG higher (over 5 - to follow more on my desired tokens), the Skintones are changing to more unnatural "red/grey" and the 3d-ish effect grows dramatic. Also the double-penis glitch is growing. .. The Skintones are than very difficult to shift with a VAE.
Chapeau and thank you for this model. Heartsmiley.
Thanks man for going into detail and posting that image with the 3 samples, I think I got the penis problem solved without the use of loras and Iv reduced the quality a touch so it shouldn't be so touchy when it comes to that 3dishskin tone. also Thank you very much for the buzz......im not sure what it does.....but thank you greatly for it anyways.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.