CivArchive
    Preview 840776
    Preview 840778
    Preview 840775
    Preview 840780

    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

    Refined v11 Dark

    Noise offset version of the main model (v11).

    Place config file (.yaml) in same folder as model (.safetensors)

    Make sure config name matches the model name, minus file extension.


    Note : Use lower CFG than main model. Between 6 and 7.5

    What's included :

    • Refined_v11_Dark.safetensors | Main model with Noise offset | FP32 | Safetensors

    • Refined_v11_Dark.yaml | Config

    • Refined_v11_Dark.ckpt | Main model with Noise offset | FP16 | PyTorch (.ckpt)

    FAQ

    Comments (7)

    Ant6431Jun 2, 2023
    CivitAI

    Your models are king of king! Can you upload 1.99gb safetensors for the following? I tried to convert them myself but all failed. I'm poor with computer. [1.99gb models missing safetensors - project aio, cine diffusion, refined dark, electric eden, electric eden dark, eris] I know it's a lot. sorry.

    kalouthecutest542Jun 5, 2023· 2 reactions
    CivitAI

    Doesnt work for me. I just get pixelated images of wierd colours. Any advice?

    Ben4ArtsJun 6, 2023

    Have the same Problem - just mainly RGB pixelated images as outcome.

    ferchoramaJun 21, 2023

    Did you download the .yaml file?

    Ben4ArtsJun 22, 2023

    Yes - its in the same directory. Also downloaded both again to insure both are ok...

    AgaperSep 26, 2023· 2 reactions
    CivitAI

    https://prnt.sc/VNF7LoNjOxs- Good afternoon - the model does not work - help me solve the problem

    ferrrett33Apr 27, 2026
    CivitAI

    This doesn't work like other models in ComfyUI, gives junk pixel images unlike 80+ others tested with the exact same settings.

    Checkpoint
    SD 1.5

    Details

    Downloads
    801
    Platform
    CivitAI
    Platform Status
    Available
    Created
    5/19/2023
    Updated
    5/11/2026
    Deleted
    -

    Files

    Available On (1 platform)

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