CivArchive
    Doomer Boomer - v1.0
    NSFW
    Preview 1768269
    Preview 1768171
    Preview 1768146
    Preview 1768188
    Preview 1768155
    Preview 1768177
    Preview 1768179
    Preview 1768198
    Preview 1768200
    Preview 1768217
    Preview 1768234
    Preview 1768239
    Preview 1768243
    Preview 1768244
    Preview 1768252
    Preview 1768255
    Preview 1768256
    Preview 1768299
    Preview 1768261
    Preview 1768310

    Doomer Boomer

    A 1980s - 1990s fantasy/sci-fi RPG art model.


    If you're family with my other models you might be asking yourself, haven't I seen this before?

    So here's a quick breakdown of the differences between seemingly similar models :

    Electric Eden : My first attempt at creating a 80s - 90s RPG style art model. Using a small sample model (trained on a small portion of the full dataset) and then merged with a few other models to makeup for being undertrained.

    Another Damn Art Model (ADAM) : Further trained the model from Electric Eden and merged different epochs to bring out elements from each epoch that I liked. Still trained on a sample set of the main dataset.

    Doomer Boomer : Unhappy with some of the results in Another Damn Art Model (ADAM); I reevaluated my dataset. Completely starting over and creating a new training set. This time, using 768x768 images instead of 512x512. I also focused on structuring my training set so that's it's more organized, using data processing techniques to clean the directories and ensure that there wasn't any artists images being wrongfully attributed to another.

    I also increased the number of quality images from each artists. At the coast of reducing the number of artists down to exactly 10 artists (you can see a list of them bellow). Once again, this model is still not using the full (new) dataset. This was trained on yet another sample dataset for testing purposes. Pleased with the results I was seeing, I decided to release it here.


    Questions/Feedback/Updates?

    Visit my thread on the Unstable Diffusion Discord


    Artists :

    • Boris Vallejo

    • Brom

    • Frank Frazetta

    • Frank Kelly Freas (or just Kelly Freas, for tagging)

    • Hajime Sorayama

    • Luis Royo

    • Milo Manara

    • Olivia De Berardinis

    • Philippe Druillet

    • Simon Bisley

    Simply add by in front of the artists name in the prompt to trigger their style.

    For example, by Simon Bisley

    If the style isn't strong enough. Use attention/emphasis; (by Simon Bisley:1.2)


    VAE Required - Download it here

    (the full model will have it's own fine-tuned VAE).

    Install :

    stable-diffusion-webui -> models -> VAE

    In Webui :

    Under Settings -> Stable Diffusion -> SD VAE select the downloaded VAE and uncheck Ignore selected VAE for stable diffusion checkpoints that have their own .vae.pt next to them


    Settings

    Quick Settings :

    • Settings -> User interface -> Quicksettings list

    • sd_model_checkpoints sd_vae CLIP_stop_at_last_layers s_chrun always_discard_next_to_last_sigma

    ETA Noise Seed Delta :

    • Settings -> Sampler parameters -> Eta noise seed delta

    • 31337

    Sampler Method :

    • DPM++ SDE Karras

      • Sampling steps = 25 - 40

      • CFG = 7 - 9

    • Euler a

      • Sampling steps = 20 - 30

      • CFG = 6 - 7.5

    These are just recommendations. Feel free to experiment with other samplers and different parameters.


    Hires Fix

    Models :

    Install location : stable-diffusion-webui -> models -> ESRGAN

    Hires Fix Settings :

    For all ESRGAN models (which the above are) I use the following settings :

    • Upscale by

      • 1.5 if resolution is > 512x768

      • 1.6 if resolution is <= 512x768

    • Denoising strength

      • 0.25 - 0.35

    • Hires steps

      • If sampling steps > 60 then,

      • Hires steps = half of sampling steps.

      • for example, sampling steps = 80, then Hires steps = 40.


    ADetailer

    Extension for webui that uses ultralytics to 'fix' faces/hands/body after generation.

    Download here - https://github.com/Bing-su/adetailer

    Read the information in the GitHub repo linked above for more info and installation guide.


    Check out my other models :

    SDXL

    SD1.5

    LoRA

    Description

    Initial Release

    FAQ

    Comments (17)

    VandalgoghJul 30, 2023· 1 reaction
    CivitAI

    Did you include art from dorian cleavenger? if you are going to keep polishing this model, it would be great

    ndimensional
    Author
    Jul 30, 2023· 2 reactions

    Dorian is part of the full dataset, but not in the dataset used to train this sample model.
    Future versions of the model will include his style. 👍

    frfromgJul 31, 2023· 1 reaction

    @ndimensional Please don't give up on Cine Diffusion as well, very underrated checkpoint.

    frfromgJul 31, 2023· 1 reaction

    Also, who knows, this might give you some ideas:

    https://civitai.com/models/38199?modelVersionId=44168

    both pick up Sorayama keyword and work quite well.

    ndimensional
    Author
    Jul 31, 2023· 1 reaction

    @frfromg Thanks!
    I've been slowly working on rebuilding the database for cine diffusion, plan on training it at a higher resolution with a lot more data.

    ndimensional
    Author
    Jul 31, 2023· 1 reaction

    @frfromg ohh, I like.
    The Sorayama dataset in this model is quite large. Unfortunately, I think I accidently trained his style on a the pre-manual-caption dataset, so the tags weren't as good. I'll fix that soon in a update.

    frfromgAug 1, 2023

    @ndimensional Sorayama is one of the best artists out there, therefore good news :D

    VandalgoghAug 5, 2023

    @ndimensional Is moebius in this set too? i don't remember if it was in this model or in other one

    JellonAug 1, 2023· 1 reaction
    CivitAI

    This looks super dope. I'm super excited to give this a try!

    fengpiaoyi000Aug 8, 2023· 1 reaction
    CivitAI

    Pay attention to you for a long time, this is what I have always wanted

    CrisdaxAiAug 17, 2023· 4 reactions
    CivitAI

    i have a problem the pictures have excessive saturation , how can fix it?

    Thanks

    Boris401Aug 17, 2023· 1 reaction

    I was having the same problem, then I looked and realized I hadn't followed the settings info in the description. Adding the 'always discard next to last sigma' to the UI and making sure it was checked after restart seems to have solved the trouble. Hope this helps.


    Quick Settings :

    - Settings -> User interface -> Quicksettings list

    - sd_model_checkpoints sd_vae CLIP_stop_at_last_layers s_chrun always_discard_next_to_last_sigma

    ETA Noise Seed Delta :

    - Settings -> Sampler parameters -> Eta noise seed delta

    - 31337

    113346Sep 2, 2023
    CivitAI

    WOULD LOVE ONE with art trained with cyberpunk 2020 artists

    spunkymcgooOct 5, 2023· 5 reactions
    CivitAI

    This reminds me of when SD 1.5 first came out, before everything got filtered down to basic photorealism and SD could still do something that looked different

    piespe609Dec 8, 2023· 2 reactions
    CivitAI

    wonderful for us old school. I wonder if you covered Mordillo in any of your model

    4180611Jul 7, 2024
    CivitAI

    Bro, this is so freaking cool!

    NourdalAug 19, 2024
    CivitAI

    This model is really cool! Even without using artist tags, it still gives the image a nice expressive old-school illustrative shade. In addition to this, it has a good anatomy and excellent responsiveness and copes with a wide variety of tasks (except that it has a slight bias towards femininity). Great job! Thanks!

    Checkpoint
    SD 1.5

    Details

    Downloads
    4,237
    Platform
    CivitAI
    Platform Status
    Available
    Created
    7/29/2023
    Updated
    5/13/2026
    Deleted
    -
    Trigger Words:
    by Boris Vallejo
    by Brom
    by Frank Frazetta
    by Hajime Sorayama
    by Kelly Freas
    by Luis Royo
    by Milo Manara
    by Olivia De Berardinis
    by Philippe Druillet
    by Simon Bisley

    Files

    doomerBoomer_v10.ckpt

    Mirrors

    CivitAI (1 mirrors)

    doomerBoomer_v10.safetensors

    Mirrors

    HuggingFace (1 mirrors)
    CivitAI (1 mirrors)

    doomerBoomer_v10.safetensors

    Mirrors

    CivitAI (1 mirrors)

    Available On (1 platform)

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