CivArchive
    Preview 126447027
    Preview 126447572
    Preview 126447356
    Preview 126447057
    Preview 126447918
    Preview 126447056

    This Checkpoint is under construction!

    Please read this post 😌


    Note about v9.6:

    Facing problems in results, probably I'm training a lot of concepts at the same time.

    And to make matters worse, GPU prices have increased ridiculously in a short time. I had started training on an RTX 5090 paying $0.22/h and now it's over $0.50/h. The RTX 4090 is at least $0.28/h.

    I appreciate the people who are sending credits on Vast.ai, but with these current GPU prices, I'll have to wait a while before continue... And if the prices don't go down, then I'll continue. Please don't forget to contribute πŸ’œ


    All sample images are zero-shot generated

    I will always try to avoid prompts that are similar to those used in the dataset. This way, I can show you the progression and quality of learning, making it clear that the model is learning the concepts and not just memorizing the images.

    Even though no faces were blurred or removed from the images in dataset, you'll still see that it will always generate random faces (you won't see Mia Khalifa or Kendra Lust in the generated images 😌)


    The images generated by this model are not at an acceptable level, so don't expect extraordinary results (yet).

    ❌ = Not available yet

    πŸ”΄ = Worst

    🟠 = Not good

    🟑 = Almost there

    🟒 = Good

    🟣 = Perfect



    Training now πŸš€

    1. Sex normalization

    2. Penetration control

    3. Fingering control

    4. Refine Base NSFW


    Available in beta v9.5 (preview)

    Concepts to be implemented at final version:

    1. Anus 🟑

    2. Back view 🟑

    3. Breasts size control (small, medium and big) 🟑

    4. Black penis 🟒

    5. Blowjob 🟑

    6. Cum in mouth 🟒

    7. Cum on face 🟒

    8. Pussies 🟒

    9. Doggy-style (dedicated) 🟑

    10. Fingering 🟑

    11. General sex positions (Missionary, Doggy, Spreading, POV, etc) 🟑

    12. Groping ❌

    13. Hard nipples (need more images) ❌

    14. Naked man 🟒

    15. Panties aside (need more images) 🟠

    16. Playing with pussy (Rubbing, touching, etc) 🟑

    17. POV (dedicated) πŸ”΄

    18. Pussy closeup 🟒

    19. Removing clothes 🟑

    20. See through (need more images) ❌

    21. Penis control (flaccid, hard, small, medium, big, thin, thick, etc) 🟒

    22. Text 🟒

    23. Weird things (Funny and weird images, like "stepsister stucked in washing machine" 😏) πŸ”΄

    24. Wet clothing (need more images) ❌

    25. Female masturbation (hands inside shorts, panties, skirts, etc) 🟠

    26. African women (need more images) 🟒

    27. Normalization (simple prompts for complex things) 🟠


    Concepts to be incorporated soon

    1. Sex with panties aside (dedicated)

    2. Big breasts (to improve breasts-size control)

    3. Sexy clothing

    4. E-girls

    5. Cosplay

    6. Amateur Selfie

    7. Wide hips (with narrow waist)

    8. Chubby women

    9. Fat women

    10. Interracial sex (dedicated)

    11. Femboys and Tomboys (dedicated)

    12. Public (dedicated)

    13. MILF

    14. Lesbian (dedicated)

    15. Teasing

    16. Gangbang

    17. Footjob

    18. Cameltoe

    19. Bathroom (dedicated)

    20. Asian (dedicated)

    21. Nature (dedicated)

    22. Gay (dedicated)

    23. Spanking/Discipline

    Items marked as "dedicated" are already present in the dataset, but more images are needed for better learning.


    How about helping to make the dataset?

    There are many concepts and fetishes, and I don't know all of them and may not even be able to remember most of them, so you can suggest a concept to be included in the model.

    You can just suggest the concept or send images/links of the concept to my HuggingFace on LoRA Requests community.


    The Checkpoint Purpose:

    I'm trying to bake the best SFW + NSFW Base Model.

    I focused heavily on regularization so that the NSFW wouldn't end up leaking and contaminating the native SFW side of Flux. To do this, I needed to create a large regularization dataset, which significantly delays training, making it more expensive πŸ˜₯

    And of course, I'm not adding knowledge, I'm replacing knowledge that is less used to make room for NSFW.

    My intention is to make this model incapable of producing anime-style images, so we will have "more space" for realistic NSFW content and prevent Flux from forgetting how to do other things, such as writing text and editing images (called "catastrophic forgetting").

    So it's very likely that in the future we will have one Base Model just for realistic NSFW and another just for 2D-style NSFW.


    Want to help me continue?

    Buy PaidCoins at Aisha-AI.com and sent them to account number 2

    or

    Create an account on Vast.ai using my referral code (https://cloud.vast.ai/?ref_id=212422), top up your account, use the option to transfer the balance to another user and provide my ID: 212422


    Total spent on this Checkpoint:

    $350 USD (😭😫)

    Description

    You'll see that some preview images in this version aren't great, and that's intentional so you can compare the checkpoint progress. The image that's bad today might be perfect in the next version 😎

    This is the seventh version, but the second one I'm making public.

    This version is not yet stable, and it's here only for you to follow the progress of the model's training.

    What works in this checkpoint?

    Not much... 🀠

    We only have a few concepts and little REGULARIZATION, which should be the most important part of this model. These last few days I've spent a LOT of time looking for good quality images and creating very precise captions manually and validating them one by one in the original Flux model so as not to spoil the original database, making the NSFW content an EXTENSION and not a SUBSTITUTE for the extremely high-quality base training, done by our beloved Black Forest Labs 😎

    And it's worth remembering, I'm not using any LoRA or checkpoint from anyone else. Everything is being done from scratch on top of the original model.

    β„Ή This is a distilled version πŸš€

    CFG: 1 (This is, and always will be, the standard parameter for distilled models)

    Steps: 4 to 8

    FAQ

    Checkpoint
    Flux.2 Klein 9B

    Details

    Downloads
    500
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    4/5/2026
    Updated
    6/8/2026
    Deleted
    6/3/2026

    Files

    aishaNSFWFlux2Klein_betaV7Comfyui.safetensors

    Available On (1 platform)

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