CivArchive
    FinePorn v4 - TURBO | FP8 | INT8 | - v4
    NSFW
    Preview 138428916
    Preview 138447534
    Preview 138446915
    Preview 138447428
    Preview 138448123
    Preview 138448408
    Preview 138447739
    Preview 138447985
    Preview 138452378

    PLEASE READ THE VERSION NOTES
    What this is?

    A turbo checkpoint merged for the perfect balance between three things: NSFW capability, prompt adherence, and a "smartphone-like" look. The goal is a balanced crisp, casual image. This is the goal, and this checkpoint is the starting point; expect many updates with high frequency.

    About FinePorn

    This is an approachable but functional starting point. To hit the target, I baked in LoRAs with balanced weights + INT8 and CONVROT to achieve faster speed and good quality, with the plan to scale up future versions by adding new LoRAs, rebalancing weights and hunting for the optimal settings.

    Baked LoRAs Changelog (v4):

    All baked LoRAs will credit their creators.

    V1

    • res_2s + beta -> More Quality

    • er_sde + beta -> More Speed

    • CFG: 1

    • Steps: 8–10

    • Workflow v1

    V2

    • SamplerER_SDE + beta -> Fast and Stable

    • CFG: 1

    • Steps: 8–12

    • Workflow v2

    V3

    V4

    📐 Resolutions

    I found that scaling resolutions by x1.25 and x1.5 gives better results:

    - 832x1216 standard 1040x1520 optimal 1248x1824 recommended

    - 896x1152 standard 1120x1440 optimal 1344x1728 recommended

    - 1024x1024 standard 1280x1280 optimal 1536x1536 recommended

    💡 Notes

    Good results are achievable without a face detailer or extra passes. With the right config, some patience, and a bit of seed luck, you can get great things.

    I highly recommend start all your prompts using a phrase like this or similar.

    This is a casual, low-quality photo
    this is an amateur photo taken from smartphone, casual photo

    ⚠️ Important disclaimer

    This is NOT trained by me and is NOT my own work, my job here is using my experience to bake balanced weights of my personal taste to achieve desired images using my prompt style. My only role is to share with you what, to my eye, is the best style and quality achievable with this model. All baked LoRAs credit their creators.

    ABOUT PROMPTS

    I'm a bit dissapointed tbh, i've seen a dozen of 'big' creators and model makers just copying my hand-made prompts and spiting them on their showcase photos, with zero quotes to me or at least a small comment or a dm, it feels bad and very lazy coming from them.

    so, from now on, complex prompts will be shared only on DMs freely, but i'll keep simpler prompts public.

    Description

    More capable version, Less unwanted stuff, Forced the dropplets reduction.

    Baked LoRAs Changelog (v3 FIX):

    FAQ

    Comments (15)

    NoobFromEgyptAug 1, 2026· 1 reaction
    CivitAI

    What is the diff between FP8 | INT8 ... generating speed?

    simonishere
    Author
    Aug 1, 2026· 2 reactions

    yes, mostly generation speed, INT8 is faster and optimized for RTX 2xxx and 3xxx series

    LG89Aug 1, 2026

    @simonishere So int8 is converted from the fp8 model? Or bf16? Because the best thing about int8 is that it keeps the full model quality

    simonishere
    Author
    Aug 1, 2026· 1 reaction

    @LG89 it is converted from bf16 turbo

    sriramakumar7799888Aug 1, 2026· 1 reaction
    CivitAI

    Another brilliant model. V4 is too good.

    apo1sAug 1, 2026· 2 reactions
    CivitAI

    Can we get bf16 ?

    simonishere
    Author
    Aug 1, 2026

    yes, i'm working on it

    herkus_baronas631Aug 1, 2026· 2 reactions
    CivitAI

    Good model. It doesn't create what is not needed, but creates what I ask for. It understands requests well, although there are problems with the anatomy in further angles. But overall one of the best models. In fact, it's hard to say which model is better than which. I've uploaded some images, so it's up to you to decide whether that model is good for regular activities or not.

    the__RealistAug 2, 2026
    CivitAI

    Question about the trigger words please,
    It is mandatory to add all 3 in the prompts?
    Thanks.

    simonishere
    Author
    Aug 2, 2026· 1 reaction

    those are optional, i just paste there words that was useful for me, you can ignore them

    the__RealistAug 2, 2026· 1 reaction

    @simonishere Thank you for the clarification and quick response.

    the__RealistAug 2, 2026

    @simonishere one final query, is there a specific Text-Encoder and VAE you would recommend for optimal results?
    Currently using 'Huihui-Qwen3-VL-4B-Instruct-abliterated' and 'wan 2.1' for vae.
    Thanks again : )

    simonishere
    Author
    Aug 2, 2026

    @the__Realist not really, Krea 2 with standard encoder and vae is very powerful, i would recommend improve prompting, Krea understands many formats different and you can even combine multiple languages in the same prompt,

    the__RealistAug 2, 2026· 1 reaction

    @simonishere Thank you. Looking forward to creating with your model.

    simonishere
    Author
    Aug 2, 2026
    CivitAI

    Testing bf16, coming in one or two days maybe :)

    Checkpoint
    Krea 2

    Details

    Downloads
    2,131
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/1/2026
    Updated
    8/3/2026
    Deleted
    -
    Trigger Words:
    this is an amateur photo taken from smartphone, bad quality photo
    The lighting is clear, soft diffused
    the details are sharp, and the feeling of the photo is casual and spontaneous.

    Files

    finepornV4TURBOFP8INT8_v4.safetensors

    Mirrors

    finepornV4TURBOFP8INT8_v4.safetensors