CivArchive
    Raemu Flux - v1.0
    NSFW
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined

    Raemu Flux

    A finetuned model built on top of Flux.1-dev, specifically focused on anime. It has been finetuned with dataset nearly 1,500 carefully curated, high-quality aesthetic anime images, resulting in noticeable improvements in anime scene rendering and visual quality.


    Enjoying my work? Consider supporting the development of my models by buying me a coffee on Ko-fi

    Also check out my other models on Mage: Raepix Focus XL / Raepix Focus XL Lightning / Raevitamix Realistic / Raevista XL


    The model does not include VAE and CLIP, which are essential components. You must have them.

    *Baked version already included all clips and vae.

    Download both clip_l and t5 from here and place them in the respective folders: text_encoder for ForgeUI and clip for ComfyUI.

    • steps: 20 - 30

    • Distilled CFG/Guidance: 3.5 - 4.0

    • CFG: 1.0

    • Sampler: euler/dpm++ 2m simple

    • Vae: flux ae

    • clip: clip_l and t5xxl

    Usage

    Be sure to include "anime" in your prompt; otherwise, the output may appear realistic. For example: "A woman anime hold sign that says Hello World."

    License

    The model falls under flux-1-dev-non-commercial-license

    Description

    Initial release

    FAQ

    Comments (8)

    DazrockSep 15, 2024
    CivitAI

    Am i missing something here?
    I'm using the latest version of Forge with this model. I have The T5 encoder installed, along with the ClipL, and the VAE. I use Regular Eluer + Simple.
    Clip Skip 1, and i STILL get blank images.
    Does anyone got any idea what i'm doing wrong here? It's driving me up the flaming wall.

    Raelina
    Author
    Sep 15, 2024

    Which version did you download? Have you already followed the recommended settings, such as distilled CFG, CFG, and step? You can simply copy the parameters from the showcase image to your Forge UI (all showcase images is generated using ForgeUI). If you've downloaded the FP8 version, try setting diffusion in low bits to automatic

    DazrockSep 15, 2024

    @Raelina Thx for replying m8. Yeah i followed all the rest. I DL'ed the FP8 btw. I also set it to the corresponding fp8 format in Forge to run the model, and also tried running it in Automatic too, and it shows a black image every time.

    OtakuStorm_AiSep 15, 2024· 3 reactions
    CivitAI

    11 GB? WTF

    Raelina
    Author
    Sep 15, 2024

    Yes, this is based on Flux model

    OtakuStorm_AiSep 15, 2024

    @Raelina Let's hope that the weight will decrease later on, otherwise a 4TB SSD would be needed here XDDD

    Tozi_WhiteSep 17, 2024· 2 reactions
    CivitAI

    This model is NSFW ready?

    Raelina
    Author
    Sep 18, 2024· 2 reactions

    Unfortunately no

    Checkpoint
    Flux.1 D

    Details

    Downloads
    1,918
    Platform
    CivitAI
    Platform Status
    Available
    Created
    9/15/2024
    Updated
    5/13/2026
    Deleted
    -
    Trigger Words:
    anime