CivArchive
    Preview 25817029
    Preview 26030064
    Preview 26030552

    Please consider buying my two albums Sisters of the Wicked and Danger Ahead, my book Dracula and also please check out my YouTube channel. Civitai won't support creators, so any purchase is a real help. Thanks.

    DRACULA https://www.amazon.com/dp/B0FM4DXYPL

    Sisters of the Wicked https://amazon.com/music/player/albums/B0DSJY3ZHY?marketplaceId=ATVPDKIKX0DER&musicTerritory=US&ref=dm_sh_CdyeuxIBNBDOjZ1hpB1PPJxT0

    Danger Ahead https://www.amazon.com/music/player/albums/B0DB2DV354

    Music In The Machine https://www.youtube.com/@musicinthemachine/videos

    Lora Creation: https://www.upwork.com/services/product/design-flux-lora-for-creation-of-ai-art-1909718528813429477?ref=project_share

    For the De-Distilled Model, Distilled CFG Scale should be set to 0. Then use actual CFG. For me 3.5 to 8 seem good.

    If you like the models, please follow. The page is getting crowded as I keep releasing my model in as many formats and options as I can.

    V1.1 Hyper 8-Step is now available and works in ForgeUI as well as Comfy. Schnell V1 Much faster, getting good results with 1-4 steps. Quality is not quite on the level of the Dev model, but much faster. So far it seems text is more consistently good though. New GGUF version of the Schnell model up now. Thanks to pkmngotrnr for converting them for me. Much appreciated. So far works in Comfy only at least for me. DEVfp8V1.1GGUF is now up as well. V1 version has European Flux mixed in at what seemed like a pretty low percentage, but it seems like it is a bit too strong. If you like this look, feel free to use this one.

    This is my initial FLUX model. It is base on the flux1-dev-fp8 model. This is a merge only in the sense that I merged in some Loras that I like to make it more realistic. As with all of my models, the goal is the best photo realism that I can achieve. If it will do other things well, that is a bonus. Until I can learn a lot more about FLUX, and see if at some point true merges are possible, this is a pretty good start. I don't know about compatibility with all software. I use ForgeUI and I am able to run it fine. Most gens take about a minute and a half for me at 1024 X 1328. I use Euler with the Beta scheduler or the Simple. I haven't experimented much yet with other samplers. I typically use 24 to 28 steps.

    Description

    V1.1 is a version without "European Flux," so is very open to different faces.

    I have been told that ComfyUI users have to load the model as a pure Unet and manually load in text encoders. Does not load with standard loader.

    FAQ

    Comments (8)

    beautifaiJul 27, 2025
    CivitAI

    Which base model have you used from HF ? ( For v1.69)

    Seeker70
    Author
    Jul 28, 2025

    The base model for all of my Flux 1D models is the regular Flux 1D fp8.

    az420Sep 17, 2025
    CivitAI

    Definitely one of the better Flux models on the site!

    Seeker70
    Author
    Sep 17, 2025

    Thanks

    FapperGODOct 17, 2025
    CivitAI

    Does anyone else get a poor quality image when using the negative prompt? It is still usable, but quite fuzzy/blurry, whereas leaving the negative prompt empty makes a perfect, clear image. Using CFG 3.5, 28 steps, distilled CFG disabled.

    Seeker70
    Author
    Oct 17, 2025

    Yes, Flux is meant to be used with the CFG always set at 1. In Forge the negative is unavailable when the CFG is properly set to 1. If you go up to 1.5 it will become active, but the higher you go over 1, the worse the images will be. If you really want a negative prompt, it's best to go as little over 1 as possible.

    rasputin73Dec 12, 2025
    CivitAI

    Dude, this is still one of the best Flux realism models out there! Even with no updates in 8 months, I haven't found anything better. Any plans for a "Boning" version, or further updates to "Spinning"? Your work is severely under-recognized. Thank you!

    Seeker70
    Author
    Dec 12, 2025

    Thanks. I haven't found any better than mine yet either. I haven't had much time to work on stuff lately. Although I haven't seen much new out there that looks like it would improve on mine. As for Boning and Spinning, the last update wasn't too long ago, and similarly, there hasn't been much new out there that looks like it would improve them. Now there are starting to be some new models out there like Z-Image that are looking promising, but so far, I am not having much luck making Loras that work for Z-Image Turbo. It's an awesome model though in general if you don't need specific characters with Loras. The prompt adherence is insane. I have been working a lot lately on my Sisters of the Wicked 2nd album, Come Back To Me, which is coming out Dec. 24th so that has been taking up most of my free time.