Fidēlis = faithful, loyal, true, trustworthy, dependable
Note: Preview images are generated without the use of LORAs.
About
This model is aimed for photorealism but at the same time versatile and flexible with its generations. It is mostly geared towards generating muscular men with defined muscles so it might not be as good with other body types. Also, while this model is mainly created for male-oriented NSFW stuff, it can still be used to generate SFW images..
My Settings
These are just some examples of the settings I usually use and it's not really a hard requirement so you're free to experiment and see which setting works best for you:
Sampling Method: DPM++ 2M Karras or DPM++ SDE Karras
Sampling Steps: 25 - 50
Hires. fix: On
Upscaler: ESRGAN 4x+ or 4x_NMKD-Siax_200k or 8x_NMKD-Superscale_150000_G (if you have it)
Hires Steps: I usually put it at 0 so it'll be the same as Sampling Steps
Denoising Strength: 0.25 - 0.35
Upscale: 1.5 - 2
CFG Scale: 4 - 8
Clip Skip: 1-2
Extra Tips
Try to keep the prompts short and concise. No need to fill up the prompts with unnecessary wording that does the same thing like high detail, ultra detail, absurdres, hires, photorealistic, hyperrealistic, etc. Keep it simple.
ADetailer is key if you want to get good looking faces. If you're generating a close up shot or portrait, most of the time you won't need it. But if its a full body or far shot, ADetailer is absolutely necessary unless you wanna get distorted or blurry looking faces.
Hires fix is highly recommended, especially for far and wide shots where a lot of details are getting lost. And if you're using LORAs, it is mandatory to use it because without it, the output might look a little blurry and overcooked.
Use negative embeddings instead if writing paragraphs of words into the negative prompts. Avoid using too much at once. Here are some examples of the ones I usually use:
CyberRealistic Negative (Personal fav, seems to work best for me)
BadDream & UnrealisticDream (Less realistic but more creative result)
realisticvision-negative-embedding (Pretty good as well)
Description
FAQ
Comments (16)
thanks, I've been noticing you using this. Thank you!
I've been noticing you using this too. Thank you so much!
Nice!! Thanks for putting this up! Been hoping you would!
Welcome, hope you like it ..
@Kairen92 I most certainly do!
Grazie, grazie!
Thank you for all the efforts you devoted to the men-gen community! The clothes loras were all exactly what my minds contained (when thought of one, then you post that one, amazing)!
I've met some problems with the outputs hairstyle, and I wonder maybe you would like to create a hairstyle collection focusing on men (cus there was a popular one mainly for female). For me, I love the mild curly short hair in Greece/Roman time period, just like the men in the movie 300, but I can't describe it properly and lacking stability.
Wish all your work go smoothly and succeed eventually! Can't wait to see your next porny, homoerotic or aesthetic models!
You're welcome. I'm still a little inexperienced but I wanna do what I can to contribute to the male related content creations. I can't take credits for all of the outfit ideas though, some of them are based on other's suggestions. which you can do to if there's a specific outfit in mind. If i think it's plausible, I'll try to make it if I have the time..
Hmm hairstyles? Interesting.. I've never done one before, mainly because I usually just preferred a clean short look. And most realistic models already have a decent amount of hairstyle data. But it'll be interesting to attempt a specific hairstyle though. I'll think about it..
"men gen"
☝️ 12/10
can you make a baked vae version please?
Oops, I forgot to mention, it's already baked with vae. I used vae-ft-mse-840000-ema-pruned ..
@Kairen92 Thanks !
Thanks so much for sharing this! Can't wait to play with it.
Thank you so much, hope u like it!
Just bought you a coffee to thank for this and the LoRAs… then I saw your new ChemPunk LoRA and "homo_fidelis 1.5" and of course I currently only have one need in my life. ;)
OMG, I have no words to descibe my feelings rn.. Thank you so much!! 😭😭😭