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
v4.0
What's new:
Overall improvement
Rebuild using v3.0 as the base model
Slightly tweaked the weights of some loras used
adjusted the realism to allow for more creative results
FAQ
Comments (11)
I wanted to tell you that your base model is one of my favorite base models. The results are astonishingly good. I'm learning a lot about the features and I'm a newbie. I would be happy to get tips from you about your models. Just take a look at my collection. I'm sure I'm still doing a lot of things wrong here and there. But with time, it gets better.
Aww thank you so much. I'm glad you like it. You can DM me anytime if you have any questions about it and I'll try to get back to you as soon as I can..
@Kairen92 I really appreciate your response and offer. I think that the eyes in particular look good when you work over inpaint again. That's great. Thank you for your great work.
There is a common problem: it's so hard for barefoot generation.Anyway,it's still a high-quality model, thank you so much.
working types of env. lighting:
warm golden hour lighting (indoor/outdoor scene) silhouetted against the bright sky (outdoor scene) silhouetted against the bright window (indoor scene) soft natural lighting (indoor/outdoor scene) overcast flat lighting (outdoor scene)
exact ideas ripped from mine, fuck my life I'm so shocked at the appalling piracy and savages who have no virtue and no respect for artists and I'm going to deal with it, like i have everything and I'm so sick of mindless people who have no respect and are entitled to our skills that are really the golden brains of the society, and artist are the ones who create the narrative not you, you cannot make a narrative by copying it, that's just tracing, and i see my work, its traced, no other ideas no other attempt at being the thingyou profess the artist, i wish iwas not alive for this, its been feeling like I've been raped clean every single corner of my mind and sold in other names, around the world on every site, and I'm now ignored and laughed and ridiculed and blocked for dating to challenge my rapists
Amazing mode! Keep up the good work!
thank you so much !! :)
Amazing model, realistic photos.
One problem (also for other diffusion models): mixture of racial, sometimes I want to generate two people in a picture and I specify racial of these two, but in most cases, they just mix together
I love this model but I would really like to see what type of model you could create with Flux.
Flux is massive. Absolutely massive. Its not the easiest thing on earth to convert to.