CivArchive
    Preview 96362
    Preview 96381
    Preview 96380
    Preview 96379
    Preview 96375
    Preview 96377
    Preview 96378
    Preview 96376
    Preview 96374
    Preview 96373
    Preview 96372
    Preview 96371
    Preview 96370
    Preview 96369
    Preview 96368
    Preview 96367
    Preview 96366
    Preview 96365
    Preview 96364
    Preview 96363

    Like photorealism? Try my new fine-tune 'Lomostyle'

    Merged Model with slight fine-tuning focused on human anatomy and skin texture, can also be used as a general purpose model. v10 is a foundation that will be further built upon with more mergers + fine-tuning.

    List of models used in merge can be found in the version description.

    Limitations (as of now)

    • Photos of Men

    • Anime

    • SFW generations without specific tags

    Trigger Words

    Trigger words are not required.

    However, the following tags can be used to alter the generation.

    analog style, modelshoot style, wa-vy style, synthwave, sci-fi, cyborgdiffusion, erect penis, flaccid penis, postapocalypse, 3d, render, nsfw, sfw

    For tags like "nsfw", "sfw", "3d", and "render", you can swap these between your positive and negative prompts to get more specific outputs.

    For example, putting "sfw" in your positive prompt, and "nsfw" in your negative prompte will push the model in the direction of generating sfw outputs. You can also add/decrease attention using ()and []

    Textual Inversion (TI)

    Many of sample images include a negative textual inversion that helps fix things like hands, ect.. This isn't a requirement, I've tested the model without this TI and didn't have any issues. I do recommend using it though, as it does help.

    Bad Prompt TI - https://huggingface.co/datasets/Nerfgun3/bad_prompt

    I recommend using Version 2 and setting it's weight to 0.8 in the negative prompt; (bad_prompt_version2:0.8)

    For webui, bad_prompt_version2.pt goes in:

    sd/stable-diffusion-webui/embeddings

    Hires Fix

    I used Hires Fix for many of the sample images. This is not a requirement but it does seem to improve results. I mainly use latent(bicubic antialiased) with Denoising strength set to 0.65.


    Check out my other models

    SDXL

    SD1.5

    LoRA

    Questions or Feedback?

    Visit my thread on the Unstable Diffusion Discord Server

    Description

    Initial Release

    VAE not required.

    Models used in merge:

    Copious experimentation with UNet Block swapping was used in the creation of this model.

    Note: The model name for the samples may read "refined-WRAP8". This was the original name of v10 during testing.

    Dreamlike license inherited from POV Skin Texture model

    I'll replace the Skin texture model with my own fine tuned skin texture model in the next version.

    FAQ

    Checkpoint
    SD 1.5

    Details

    Downloads
    5,804
    Platform
    CivitAI
    Platform Status
    Available
    Created
    2/13/2023
    Updated
    4/23/2026
    Deleted
    -

    Files

    refined_V10.safetensors

    Mirrors

    refined_V10.ckpt

    Mirrors

    CivitAI (1 mirrors)

    Available On (1 platform)

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