CivArchive
    Quintillus - "Reality" - v1 - The Beginning
    NSFW
    Preview 51065334
    Preview 51065341
    Preview 51065312
    Preview 51065339
    Preview 51065329
    Preview 51065311
    Preview 51065308
    Preview 51065320
    Preview 51065336
    Preview 51067727
    Preview 51065325
    Preview 51065172
    Preview 51065316
    Preview 51065328
    Preview 51065335
    Preview 51081019


    Older Description for v2 and v1 -

    This checkpoint is made to retain most of the knowledge of base Illustrious/Noob while making everything as realistic as possible.

    --Prompts have been attached to all of my gens--

    I had one vision when I started working with Illustrious - creating a realistic merge that did not ruin the base model's extensive danbooru knowledge.

    Prompts for the showcase images have been taken from all the best Illustrious model showcases and galleries. All showcase images for this model are one shots with random seeds and one hires fix. No Adetailers or inpainting has been used for those. In most cases, v2 feels way more real as the faces are much less anime-ish now. If you want the skin to be like v1, just use the suggested LoRA at 0.4 strength.

    V1 has some problems with residual noise and general clarity. V2 should have more depth to its "realism", and should offer better compositions and quality in general as compared to the first version. Do try it out. (The first version can still be quite unique for "grainy" gens).

    USAGE GUIDE:

    Now, here's some tips for squeezing the most amount of realism from this checkpoint (these are just my observations, feel free to experiment):

    • Make sure that you use lower values for your CFG (3-5). CFG 3 and karras works incredibly well for realism.

    • Use DPM++ 2M with the "Beta" or "Karras" scheduler, and do a highres pass at 1.5x at 0.33 denoise and half the original steps. (Please experiment with different sampler and scheduler combinations if you can).

    • Remove all instances of artist names and other "painted" styles from your prompts (unless they tend towards realism).

    • For the positive prompts, include this in the first part (Kinda IMPORTANT):

      Optional - "cinematic lighting"

      real, 4K, RAW, photoreal, DSLR photo, real skin,
    • For the negative prompts, maybe use this?

      cropped, lowres, worst quality, sketch, unfinished, greyscale, faded, low saturation, jpeg artifacts, watermark, text, anime, CGI, 2D

    Online run on Tensor -

    RUN ON TENSOR

    (Generating onsite on Tensor gives the gens a grainy look (v1 only), making them even more real. Absolutely no idea why this happens.)

    This model responds to prompts really well, and in a similar fashion to base Illustrious/NoobAI models. This also implies that you can use artist styles in your prompts for uncertain ways in which the realistic part gets affected.

    v1 Related:

    Now, some of you might not call this model very "realistic", but it certainly does have that 3D style that I really love. The end goal is always to achieve more realism, while making sure that the model's base knowledge is not disturbed.

    There are other Illustrious based models that can provide you with more actual "realism" (debatable), but all of them have to sacrifice some of the model's incredible compositional and conceptual abilities. Some models lose character knowledge, some lose the character clothing knowledge, the dynamic compositions, the multi character abilities and much much more in search of truly realistic outputs.

    And that is exactly what I hope to avoid with my merge, keeping almost everything in the model, while bringing the knowledge of the 3D world into it, and slowly increasing the realism.

    If you want to support the creation of more models like this, or you just like what you see (I could REALLY use it): ko-fi (。♥‿♥。).

    Also, no plan on charging early access for this one, so buzz donations are appreciated a lot too.

    Models Merged (Credits and respects to the original authors of these models for allowing sharing merges) -

    ReallyIllustrious (base) - TrueToLife_Fauxto

    Alchemist Mix (Creative Realism) - Urameshi

    babel-illustrious - BABELLA

    coco-Illustrious-NoobAI-XL-Style - COCO_OIOI01

    Illustrious_Sky-(rim) 3D - stableskynet171

    Silence_Mix - sihotan

    PornMaster-Pro 色情大师- Illustrious - iamddtla

    CyberIllustrious | CyberRealistic - Cyberdelia

    TAME Pony: The Authenticity MachinE (v2) - zyxt99565

    IllustriousSat-Real - Sateluco

    Quintessence (Magnum Opus) - Realism | The Delicate Balance | PDXL - Me

    ReallyBigLust - Illustrious Realistic - Hikarias

    Willy's Noob Realism - willywizard

    Uncanny valley (v1 D) - meden

    Description

    FAQ

    Comments (5)

    Light7799Jan 12, 2025· 5 reactions
    CivitAI

    The faces look very anime, but the skin looks so good in these pics, usually even the most realistic models has that 'plastic-y' looking skin, or just looks 'too' perfect, like no flaws and makes it uncanny. Excited to see where this model leads to.

    LazmanMar 30, 2025· 2 reactions

    That's cuz of the Major pruning of 1.0. If you check out the SDXL 0,9 model(it's typically 13gb or so, but there's a proper pruned version on here that's around the size of the 1.0 models but keeps benefits of 0.9), anyways, if you check that out, it's not always great with anatomy, but it did do better at realism in the sense you're talking about. They pruned and censored so much when they made 1.0 that they removed it's ability to do true realism. But the Illustrious realism models are on the right track to bringing that back, but with better body accuracy.

    Light7799Mar 30, 2025

    @Lazman Ah, that makes a lot of sense. I remember people wondering why people were trying to get the 'unfinished' product, and so much so 0.9 wasn't even supposed to be released, but was leaked. I was pretty sure they'd censor it in some way but I didn't realize that it was real skin. Glad to know I'm not going crazy thinking something was just 'off' and I couldn't place my finger on it. Appreciate you enlightening me.

    LazmanMar 30, 2025· 1 reaction

    @Light7799 No prob. Appreciate being appreciated, lol. And fully get you on the "wondering if I'm just nuts" thing. I think that's becoming a lot more common post-covid.

    Plus, AI can have that effect on people. Cuz it's so damned random, and certain keywords or Loras or specific models, or even different workflows, controlnets, ipadapters, ect. can really make or break your entire experience with image generation.

    Some days I get a non-stop flow of everything I want, other days I get the opposite, a non stop for of exactly what I didn't want, didn't prompt, and possibly even promotes gag reflex..

    I mean, apart from getting the opposite of the sexy content you ask for, which is off-putting in itself, AI can produce some real nightmare fuel images.. the kinda stuff that makes the elephant man(John Merrick, severely malformed man from the 1920s) look handsome in contrast.. 😦😧😨😱🤢🤮

    bunnyhuntercycy188Jan 12, 2025· 5 reactions
    CivitAI

    OMG, this one is O_O, very great job here, congrats !!!

    Checkpoint
    Illustrious

    Details

    Downloads
    373
    Platform
    CivitAI
    Platform Status
    Available
    Created
    1/12/2025
    Updated
    5/14/2026
    Deleted
    -

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.