Photos & Videos Ai Hunks - Diffusion generated stunning hotties

Would anyone else be interested in a LoRA for "average" male bodies? I'm thinking of making one because no matter what I prompt, the unrealistically muscular builds are too overweighed.
Try Realistic Vision. Using keywords in your prompt, you can make the subject more or less muscular, thin, chubby etc. I used it to generate this guy's "normal" body by specifying "age 20" and "slim body".
 
"Welcome to hell. You got here because of your dirty mind and jerking off to A.I. pictures too many times.
Your punishment is sitting on my enormous cock and getting fucked as often as I need until you can no longer cum. You'll be here for a very long time so get comfortable being bred."

00013-1611830915.png
 
Is uncircumcised penis the default for these creations or is it being added by prompts? They seem overly represented.
 
00011-33604176.png


NSFW (man), (in the style of annie leibovitz), in the city (standing in the street), (night), background is skyline, background bokeh, 18 years old, (full body shot), well-lit, volumetric lighting, rim lighting, nude, masculine, extremely handsome, pale skin, freckles, light blue eyes, lips parted, square jaw, looking directly at viewer, detailed face, detailed skin, short curly ginger hair with shaved sides, broad shoulders, narrow hips, slim build, pink nipples, hairy legs, perfect feet, ((sparse)) pubic hair, penis, (accurate male anatomy), natural color, soft shadows, rim lighting, hyper realistic, professional studio quality, award winning, lensculture portrait awards, masterpiece, 8k <lora:1ani_TGIRL_e30_n32:0.5>

Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 33604176, Face restoration: CodeFormer, Size: 512x768, Model hash: 9aba26abdf, Model: deliberate_v2, Denoising strength: 0.23, Hires upscale: 2, Hires upscaler: ESRGAN_4x, Lora hashes: "1ani_TGIRL_e30_n32: 17daffec7b44", Version: v1.3.2
 
gay bar chav
(Virile Reality with the Polaroid LoRA)
00001-840996983.png
00002-840996983.png

polaroid photo, masterpiece, best quality, male focus, 1boy, completely naked, rugged daddy, chav, stubble, (body hair:1.2), rough, dirty, Mancunian, mean, nude, boots, bare thighs, bully, druggie, skinhead, (gay bar background), (neon lights), bokeh, realistic, dramatic lighting, atmospheric, intricate detail, (penis:0.9) out, narrow waist <lora:InsPX2:0.7>,

Size: 512x768, Steps: 25, Sampler: DPM++ SDE Karras, CFG scale: 6, Seed: 473487389, Face restoration: CodeFormer, Model hash: d9911d91a2, Model: virileReality_v10, Denoising strength: 0.5, ADetailer model: mediapipe_face_mesh, ADetailer confidence: 0.3, ADetailer dilate/erode: 32, ADetailer mask blur: 4, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True, ADetailer inpaint padding: 32, ADetailer version: 23.6.2, Hires upscale: 2, Hires steps: 10, Hires upscaler: R-ESRGAN 4x+
 
I made this image and wanted to share the workflow in case you find it useful. ;)

00007-2877850997.0.png


Personally, I like to use ControlNet + some drawing tools. You can use OpenPose instead of Scribble and Depth instead of LineArt.

BTW: It's always in txt2img! and for LineArt, I use the following prompt: A line drawing, lineart, linework).

Workflow.png