CivArchive
    Preview 3593741
    Preview 3593392
    Preview 3593394
    Preview 3593396
    Preview 3593407
    Preview 3593397
    Preview 3593409
    Preview 3593406
    Preview 3593411
    Preview 3593412
    Preview 3593413
    Preview 3593414
    Preview 3593415
    Preview 3593442
    Preview 3593420
    Preview 3593434
    Preview 3593424
    Preview 3593419
    Preview 3593668
    Preview 3593757

    Here's a link to Olympus XL

    Attention: See version details for a full list of trained artists, the list is too big for the example images alone. Also, this model was trained using v pred like loss and will fry at very low CFG. I recommend using the CFG rescale extension with it.

    Version 5 is out. It is likely the last version of olympus in 1.5. If I make another one, I will likely do it in XL. In this version I increased the dataset to ~28000 curated images, trained from scratch for about 60 epochs on a cosine learning rate schedule. For best results, be thorough in your prompts. This model follows what you prompt very closely, which is good and bad. As a general rule, if you want something to appear, say it in the prompt and don't assume it will just happen. I have taken care that many uncommon tags in most models (such as pubic hair and upside-down), including many hardcore tags, are represented and working. See the example images for examples, they are straight text to image without any inpainting or adetailer. Also, make sure to use some of the 80 different artist styles available to the model. These were all trained in this version and don't require loras. That is the best way to achieve great gens with this model.

    This is my first attempt at fine tuning something. I focused on fine tuning styles and concepts that I can't easily find in a versatile base model out there,as well as providing good hentai capabilities. Model was trained on ~9k images for ~150k steps, Clip Skip 1. See example images for example concepts and styles that I finetuned in. The model is very versatile and still surprises even me. It does very well with both women and men, even though the latter does not show up too much in the example images (sorry folks, there's just too much to showcase in only 20 images). It also knows a surprising amount of characters, I encourage everyone to try out a few and see what you get. All images were generated without adetailer or inpainting of any kind, using only hires fix with 0.3-4 denoise.

    Description

    27 new trained artists. Full list:

    Ishikei

    satsuki neko

    cutesexyrobutts

    dino (dinoartforame)

    calm (artist)

    krystopher decker

    nababa

    nat the lich

    gogalking

    hungry clicker

    takayama toshiaki

    kase daiki

    sage joh

    masami chie

    bluethebone

    urushihara satoshi

    optionaltypo

    paloma piquet

    iuui

    xilmo

    stanley lau

    uo denim

    anato finnstark

    hews

    ratatatat74

    ataruman

    bartolomeobari

    Training setup:
    This model was trained for 100 epochs using the cosine learn rate scheduler in kohya. base learning rate was 4e-6. Some relevant configs:
    ```

    "max_resolution": "640,640",

    "min_snr_gamma": 0,

    "noise_offset": 0.1,

    "v_pred_like_loss": 0.75,

    "batch_size": 6
    ```

    FAQ

    Comments (14)

    asdfjkasdfasdfNov 13, 2023· 1 reaction
    CivitAI

    Interesting model for sure. Some unique gens.

    LetTheBassDropNov 13, 2023· 3 reactions
    CivitAI

    your models are legitimately the most responsive to prompts than any model I've ever used and I've tried hundreds. It also doesn't have "same face" syndrome which is refreshing. Absolute stellar work!

    rocp
    Author
    Nov 14, 2023

    Thanks, it's great to hear people like it.

    screamlouderNov 14, 2023· 1 reaction
    CivitAI

    Really well done on the model. Do you happen to have a training guide for checkpoints? There's a ton of resources explaining how to make loras but almost nothing on trained checkpoints. I would really appreciate it if you could share the settings/tools you used. Thanks.

    rocp
    Author
    Nov 14, 2023

    Sure, I'll try to write something in the main model description, look for it later (I am busy atm). But the real help here, I guess, is having a diverse and balanced dataset.

    screamlouderNov 17, 2023

    @rocp Hey just following up. If you get the time, could you please explain how you trained this model?

    rocp
    Author
    Nov 18, 2023

    @screamlouder Hey, I added some notes to the version info. It's not much, but I don't know what else to write. I usually hang around the unstable diffusion discord server. It's easier to talk over discord, so if you're ever in that vicinity, ask around for me and we can talk.

    svyatkin_pNov 23, 2023
    CivitAI

    How to fix muted colors?

    rocp
    Author
    Nov 23, 2023

    Hard to say without an example, but that usually happens because you are lacking a VAE. If you click on files for version 1.0, you can download a vae file that I recommend. Put it into your models/vae folder, then select it in settings.

    melonnarian344Nov 25, 2023· 2 reactions
    CivitAI

    Hi! first of all amazing model! I wanted to know what upscaler is recommended and what resolution i should generate with?

    melonnarian344Nov 25, 2023

    may I ask what VAE i should use?

    melonnarian344Nov 25, 2023

    and also how many hires steps

    rocp
    Author
    Nov 25, 2023

    @melonnarian344 

    A lot of questions, lol.

    I use vae-ft-mse-840000-ema-pruned as VAE, you can use whatever you like, but this one is likely the better one.

    The model was trained with bucketing, so it should be pretty flexible with generation resolution. That said, there's more data in 512x768 and 768x512 than in the other buckets, so those resolutions will likely work better.

    For the upscaler, I've been using Valar 4x from the upscalers wiki (look it up), but that's again just personal preference. A lot of people love the anime specific ESRGANs, so whatever works for you. I always leave my hires steps set to 0 to run the same amount as non-hires steps.

    I like the SDE Karras sampler at 20 steps or 2M SDE Karras sampler at 50 steps. You can experiment with others and see what you get.

    melonnarian344Dec 1, 2023· 1 reaction

    @rocp haha sorry for the inconvenience but thanks a lot man

    Checkpoint
    SD 1.5
    by rocp

    Details

    Downloads
    547
    Platform
    CivitAI
    Platform Status
    Available
    Created
    11/13/2023
    Updated
    6/11/2026
    Deleted
    -

    Files

    olympus_v10.safetensors

    Mirrors

    CivitAI (1 mirrors)

    Available On (1 platform)

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