CivArchive
    Realism by Stable Yogi Krea2 - v1.0 INT8 TURBO
    NSFW
    Preview 137112430
    Preview 137112450
    Preview 137112445
    Preview 137112437
    Preview 137112447
    Preview 137112415
    Preview 137112416
    Preview 137112424
    Preview 137112425
    Preview 137112429
    Preview 137112431
    Preview 137112436
    Preview 137112435
    Preview 137112440
    Preview 137112442
    Preview 137112444
    Preview 137112446
    Preview 137112448
    Preview 137112449
    Preview 137112451

     Realism by Stable Yogi · Krea2 · V1.0

    A new photoreal line for Krea2 — natural, believable and photorealistic.

    • True-to-life realism — real skin, pores, freckles, natural light, filmic depth (not AI-glossy).

    • Prompt-controlled — dressed when you ask, spicy when you ask. You're in charge.

    • Candid & editorial — portraits and full scenes both hold up.

    • Turbo — 8 steps. · Separate line from Muse (clean base, fresh realism blend).

    • Downloads: INT8-ConvRot , Q8 , Q4 , Fp8 Scaled

    • Settings: 8 steps · CFG 1 · Euler · Simple · native 1024–2048.

     Want more punch? The PRO edition on my portal is dialed up further.

    Description

     Realism by Stable Yogi · Krea2 · V1.0

    A new photoreal line for Krea2 — natural, believable, and it actually follows your prompt.

    • True-to-life realism — real skin, pores, freckles, natural light, filmic depth (not AI-glossy).

    • Prompt-controlled — dressed when you ask, spicy when you ask. You're in charge.

    • Candid & editorial — portraits and full scenes both hold up.

    • Turbo — 8 steps. · Separate line from Muse (clean base, fresh realism blend).

    • Downloads: INT8-ConvRot , Q8 , Q4 , Fp8 Scaled

    • Settings: 8 steps · CFG 1 · Euler · Simple · native 1024–2048.

     Want more punch? The PRO edition on my portal is dialed up further.

    FAQ

    Comments (15)

    abola2121Jul 18, 2026· 1 reaction
    CivitAI

    It's good for the most part, but the NSFW influence can be a bit sensitive (e.g "a man wearing jeans and a shirt fingering a woman through her panties"), but 60% of the time the man's dick will be out despite not being in the prompt.

    Stable_Yogi
    Author
    Jul 19, 2026· 2 reactions

    Got it, will fix in next update !

    GenoMachinoJul 19, 2026
    CivitAI

    Hmm... Same multi-colored static issue as before... both for the fp8 and the int8 versions... Am I doing something odd on my end? Whatever tweak you did for the Muse int8 variant works perfectly now...

    Stable_Yogi
    Author
    Jul 19, 2026

    I am running them on Forge and works perfect. Comfy works great too. I haven't seen any issues as of now.
    how to on forge is here https://civitai.com/articles/32010/run-krea-2-in-forge-free-extension-first-on-forge

    GenoMachinoJul 19, 2026· 2 reactions

    Yeah, that's interesting... I'll keep playing around with it. Super impressed with the Muse version for sure!!

    CosmicSporesJul 19, 2026

    @GenoMachino I get the same issue when using the int8-fast nodes on a lot of custom merges of Krea2. This works fine with default comfyui loader, but it's 1 minute render times vs 10 seconds with the int8-fast nodes. Doesn't seem to be any sort of settings to correct this and I think int8 fast nodes are abandoned now unfortunately since comfyui natively "supports" int8. Native support always sucks.

    GenoMachinoJul 19, 2026

    @CosmicSpores Hey, thanks for the reply and tips!! I've only seen this on 2 or 3 of the int8 versions, the other 4 or 5 work great... Including Stable's Muse after they made some tweak on it! So should I be using a different checkpoint loader in my workflow? I'm currently using the "Load Diffusion Model INT8" node... I appreciate the support! :-D

    GenoMachinoJul 19, 2026

    @CosmicSpores Hey, that was it!! The regular "Load Diffusion Model" node works just fine... yes a little slower than int8 node, but I can see the results. Funny, tho, they look a little grainier that with the int8 node... Again, thanks!!

    GenoMachinoJul 20, 2026

    @Stable_Yogi Turns out it was the INT8 Model loader that might have been giving me trouble... Your latest loads and works just fine with the standard Load Diffusion Model node... No Int8 turbo speed tho... oh well! Looks great, BTW!

    CosmicSporesJul 20, 2026

    @GenoMachino Last night, I updated my CUDA from 12.8 to 13.0, torch to 2.13, reinstalled flash attention, sageattention, triton, and all the other stuff, and reenabled dynamic vram in comfyui and I'm getting the same speeds as I was getting with the INT8-FAST node with native load diffusion model node now. I'm not sure what specifically fixed it, but it's possible to remedy this. If you decide to give it at try, maybe get your wheel files from here https://github.com/wildminder/AI-windows-whl.

    GenoMachinoJul 21, 2026

    @CosmicSpores Interesting... something to try for sure!! Thanks!!

    BenyMJul 19, 2026
    CivitAI

    Hello, great model. Could you please tell me which workflow you are using?

    penko1515Jul 20, 2026· 1 reaction
    CivitAI

    It Works very well. I use it only with 5+2 Steps (FP8 Version) and i got really Dam good Results in my opinion. Great. Its next to Moody my Favorite Model. Thanks Bro for sharing.

    Stable_Yogi
    Author
    Jul 20, 2026· 2 reactions

    Appreciate it man, thank you. And 5+2 steps is properly lean, good to hear it still holds up that low on the fp8. There's more on my portal if you wanna keep going. Cheers 🙏

    Checkpoint
    Krea 2

    Details

    Downloads
    1,803
    Platform
    CivitAI
    Platform Status
    Available
    Created
    7/18/2026
    Updated
    7/22/2026
    Deleted
    -