CivArchive
    Preview 3966534

    [Leeloo Please JPG]

    DO ME A FAVOR if you like what I'm doing...
    Please consider to test my trained models with different topics and compare it with another models in order to see if my goodies are adding anything of value to the SD world. I will be glad to get a constructive feedback about what is GOOD and what is BAD about my models.

    So, by adding the REVIEW with comments you will help me to get energy and motivation to move on.

    Thanks in Advance!!!

    !!!NotaBene!!! Load my example images to ComfyUI.

    I use complex and simplistic ComfyUI workflows with upscaling and without. To get a tips for prompts you can press a "NN Nodes" button in image resources and paste it to ComfyUI.

    Also, I often repeat some popular prompts from version to version in order to show the difference, so you can compare and get an idea of what's new.

    MAIN GOAL

    Main focus is a balance between photorealism, creativity, bokehlicious rendering with shallow depth of field, anatomy improvements, emotions, artistic and analog style.

    PS: if you like what I'm doing you can Buy me a Coffee

    Description

    CINERO XL v1.3 Alpha

    FOCUS: hands / fingers, feminine body anatomy, detailed consistent background, magic light and color effects.

    TRAINING: created uing two stages of LORA (Lycoris) training and MBW merging of the LORA into CINERO XL v1.2a with precise tuning of elemental weights. Stage 1 training performed in 8 epochs (6'664 steps with Batch Size of 2 and Gradient Accumulation steps 2 ==> 26k+ steps in total). Stage 2 with the same dataset had 10 epochs and 17k+ steps in total.

    PROMPTing tips: [TODO]

    FAQ

    Comments (6)

    liiaDec 3, 2023· 1 reaction
    CivitAI

    thank you this is a great model 💕

    antonovasvv312Dec 14, 2023· 2 reactions
    CivitAI

    wow, your model does know Alisa Freindlich?? what other actresses from Soviet movies does your model know?

    homoludens
    Author
    Dec 14, 2023· 1 reaction

    Really?!?! Didn't train on Soviet actress, but it would be good to do that. Will think about getting good dataset. Hmmmmm. Thanks for idea!

    homoludens
    Author
    Dec 14, 2023

    The picture in cartoon style really resemble the Soviet actress Alisa Freindlich, but I believe it is a coincidence or LoRa (somehow). A random luck.

    antonovasvv312Dec 14, 2023

    @homoludens  I asked because I have seen in your prompt "Alisa Freindlich" and I was wondering). Anyway, for me your model is best, so far)) keep doing!

    homoludens
    Author
    Dec 14, 2023· 1 reaction

    @antonovasvv312 unfortunately this version doesn't know Soviet Actress or singers like Alla Pugacheva. Probably it worth making the LoRa with USSR celebs...

    Checkpoint
    SDXL 1.0

    Details

    Downloads
    1,312
    Platform
    CivitAI
    Platform Status
    Available
    Created
    11/27/2023
    Updated
    4/30/2026
    Deleted
    -

    Available On (1 platform)

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