CivArchive
    Preview 120924196
    Preview 120924185
    Preview 120924184
    Preview 120924195
    Preview 120924191
    Preview 120924187
    Preview 120924186
    Preview 120924190
    Preview 120924194
    Preview 120924188
    Preview 120924198
    Preview 120924182
    Preview 120924183
    Preview 120924192
    Preview 120924179
    Preview 120924180
    Preview 120924197

    FLUX.2 KLEIN9B — Custom Merge

    Model Overview

    A custom merged model based on FLUX.2 [klein] 9B by Black Forest Labs. This model has been tested and optimized for high-quality realistic image generation with exceptional detail in textures, lighting, and atmospheric effects.

    Key Features

    • Photorealistic skin rendering with natural subsurface scattering, visible pores, and subtle imperfections

    • Exceptional water and wet surface handling — droplets, reflections, refraction, and flow patterns

    • Advanced lighting capabilities including volumetric god rays, golden hour, rim lighting, and chiaroscuro

    • Superior hair detail with individual strand rendering and natural backlighting effects

    • Rich material textures — velvet, linen, silk, leather, wood, metal, and stone

    • Strong atmospheric effects — fog, mist, steam, rain, and environmental depth

    • Anatomical accuracy for both portrait and full-body generation

    Optimal Configuration (Tested):

    • CFG Scale: 2.0

    • Steps: 15

    • Scheduler: Euler Ancestral (EulerA)

    Quick Previews:

    • CFG Scale: 1.5

    • Steps: 8-10

    • Scheduler: EulerA

    Complex Scenes (Landscapes, Materials):

    • CFG Scale: 2.0-2.5

    • Steps: 15-20

    • Scheduler: EulerA

    Resolution: 1024x1536 (portrait) or 1536x1024 (landscape)

    Best Use Cases

    • Photorealistic portraits and character art

    • Environmental and landscape photography

    • Fashion and material studies

    • Cinematic and atmospheric scenes

    • Fine art nude photography (artistic interpretation)

    • Macro detail shots

    • Water and weather effects

    Known Limitations

    • Transparent/translucent fabrics may require LoRA or enhanced prompting for proper rendering

    • Text rendering is readable but not perfect — acceptable for most use cases

    • Complex multi-element scenes may require 2-3 generations for optimal results

    • Official 4-step inference is too low for detailed work — 15 steps recommended

    Technical Details

    • Base Model: FLUX.2 [klein] 9B by Black Forest Labs

    • Architecture: Rectified Flow Transformer

    • Type: Step-distilled model (optimized for speed)

    • License: Refer to original FLUX.2 license terms

    Performance Notes

    This model excels at organic, natural scenes with complex lighting. The EulerA scheduler at 15 steps provides the best balance between speed and quality. While the official recommendation is 4 steps at CFG 1.0, extensive testing shows 15 steps at CFG 2.0 delivers significantly better results for detailed work without sacrificing the speed advantage of distilled models.

    Credits

    Base model by Black Forest Labs. Custom merge and testing by community contributors.


    Enjoy creating! If you generate something amazing, consider sharing it in the images section. 🎨

    Description

    Sorry, work in progress....

    FAQ

    Comments (20)

    Ghostj27fFeb 13, 2026· 2 reactions
    CivitAI

    I can't get this to work! a WF sample would be great

    FASCIUM
    Author
    Feb 13, 2026

    Sorry, i don't use Comfy

    nerd_bgdFeb 14, 2026· 2 reactions

    @FASCIUM Not even the provided workflows work. I am curious about what did you use to generate these images. ComfyUI is just an interface, you can emulate whatever environment the model requires. What is the magic requirement, let us know something about the model. You want us to use it, don't you? Looks promising...

    FASCIUM
    Author
    Feb 14, 2026

    @nerd_bgd all my images contains promt and all technical information, no magic

    Ghostj27fFeb 14, 2026

    @FASCIUM  what are you using? I use both ComfyUI and SwarmUI - which is similar to FORGE. When I try to generate an image I get an error each time. Would like to test this model if possible.

    FASCIUM
    Author
    Feb 14, 2026· 1 reaction

    @Ghostj27f i work only in ForgeNEO, haven't any another UI. Dont forget - its early test, some troubles is normal

    FASCIUM
    Author
    Feb 14, 2026· 1 reaction

    Correct encoder is qwen_3_8b, correct VAE flux2vae

    nerd_bgdFeb 14, 2026· 3 reactions

    @FASCIUM You should really switch to ComfyUI, that's what all cool kids use nowadays :)

    210881175Feb 14, 2026· 6 reactions
    CivitAI

    Not working in ComfyUI

    FASCIUM
    Author
    Feb 14, 2026

    Correct encoder is qwen_3_8b, correct VAE flux2vae

    210881175Feb 14, 2026

    @FASCIUM Yes, all correct but i got only noise

    nerd_bgdFeb 14, 2026

    @210881175 He uses layer skip, but I can't get it to work with it neither. Provided workflow complains about missing parameters, I believe my sfz nodes is the wrong version.
    I will investigate a bit more - alternative is the ZIT version, it works good, with similar results...

    RotoborMar 12, 2026

    Not working in ComfyUI

    sneedingonmyligma420Feb 16, 2026· 9 reactions
    CivitAI

    this could potentially be a good model but no one can use it lol

    i don't even know how that's possible, to train a model that can't be used in comfyui for whatever reason.

    CupRunethOverWithLSDFeb 17, 2026
    CivitAI

    Something is wrong with the quantization. Why don't you just provide us with the FP/BF16 version? I don't understand...

    FASCIUM
    Author
    Feb 17, 2026

    Its very specific model, found many troubles, its VERY EARLY checkpoint. Use clear model

    FASCIUM
    Author
    Feb 17, 2026

    I have my own metod of merging, with this model it works very strange

    @FASCIUM That's okay, I'm looking forward to the next versions.

    FASCIUM
    Author
    Feb 17, 2026

    @heinerheinervonvielen417 to be honest - its a long way.... very difficult customizing

    CupRunethOverWithLSDFeb 17, 2026· 1 reaction

    @FASCIUM The first usable fine tunes from SDXL appeared about a year after release. Unfortunately, this process is part of it. There will be new methods and new formats. It's going to be a great year.

    Checkpoint
    Flux.2 Klein 9B

    Details

    Downloads
    144
    Platform
    CivitAI
    Platform Status
    Available
    Created
    2/13/2026
    Updated
    5/23/2026
    Deleted
    -

    Files

    fasciumklein9b_draft2KLEIN9B.safetensors

    Available On (1 platform)

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