Diffus
始める
モデル/Flux krea dev (nunchaku svdq-fp4) Base-Model - v1.0

Flux krea dev (nunchaku svdq-fp4) Base-Model - v1.0

BlackLabe188
|
12/28/2025
|
11:14:32 PM
| Discussion|
0
Close-up of two teal ceramic cups filled with cappuccino topped with heart-shaped foam, placed on a rustic wooden table beside a potted orange flower, with a softly blurred outdoor café background including warm string lights.
Close-up black and white photo of bare feet standing on a bed of daisies with shallow depth of field, highlighting skin texture and flower petals.

推奨パラメータ

samplers

dpmpp_2m_sde_gpu

steps

20 - 30

cfg

5 - 7

clip skip

1

resolution

512x512

vae

svdq-fp4_r32-flux.1-krea-dev - nunchaku version

ヒント

Minimum VRAM requirement is about 6 GB (e.g., RTX 2060 or 3060); 10 GB+ recommended for better stability.

Use CPU offload and smaller batch sizes if VRAM is limited.

Minimum system RAM requirement is about 16 GB, with 32 GB recommended.

Flux Krea is fully compatible with LoRAs designed for Flux Dev.

Advanced text encoders like t5xxl_fp8_e4m3fn_scaled and HiDream CLIP distilled for Flux improve results.

バージョンのハイライト

Flux.1-krea-dev (nunchaku fp4)
easier for you to create masterpieces artworks

  • Minimum VRAM requirement 6 GB +

  • System-ram 16 GB +

クリエイタースポンサー

About Flux.1-krea-dev
https://docs.comfy.org/tutorials/flux/flux1-krea-dev

About Flux.1-krea-dev (nunchaku version)
https://huggingface.co/nunchaku-tech/nunchaku-flux.1-krea-dev

Discover the cutting-edge power of nunchaku-flux.1-krea-dev, the latest advance in text-to-image AI models! Built on the robust FLUX.1-dev base, this model delivers stunning, high-quality image generation with optimized efficiency through innovative 4-bit quantization technology.

With the included svdq-fp4_r32-flux.1-krea-dev.safetensors file, you can experience blazing fast inference speeds on Nvidia GPUs while maintaining excellent image fidelity. Whether you’re a digital artist, developer, or AI enthusiast, this model empowers you to create rich visuals effortlessly.

Download now to unlock:

  • Flux Krea is fully compatible with LoRAs designed for Flux Dev.

  • State-of-the-art image synthesis tuned for creative flexibility

  • Efficient performance optimized for Blackwell GPU architectures

  • Robust open-source foundation with cutting edge quantization research backing

  • Ready integration with Diffusers and ComfyUI for seamless workflow

Elevate your AI-generated art and media projects with Elevate your AI-generated art and media projects with nunchaku-flux.1-krea-dev — innovation meets artistry in every pixel.

Flux.1-krea-dev Release date : 2025.7.31

Requirement :

  • Minimum VRAM requirement is about 6 GB vram (such as RTX 2060 or 3060)

  • Recommended VRAM is 10 GB or more for better performance and stability

  • Settings like CPU offload and smaller batch sizes help when VRAM is limited

  • Minimum system-RAM requirement is about 16 GB
    Recommended system-ram: 32 GB

1) Download the Flux.1-krea-dev (nunchaku version)

https://huggingface.co/nunchaku-tech/nunchaku-flux.1-krea-dev/tree/main
----
Nvidia RTX50
svdq-fp4_r32-flux.1-krea-dev.safetensors (plz visit huggingface.co find download)

----
Nvidia RTX 20 / 30 / 40
svdq-int4_r32-flux.1-krea-dev.safetensors (Click me = Download now)
This File has uploaded at this post
---
path: \ComfyUI\models\diffusion_models\svdq-int4_r32-flux.1-krea-dev.safetensors

---
2 advanced text_encoders are recommended to make it easier for you to create masterpieces

text_encoders 1 : t5xxl_fp8_e4m3fn_scaled  (same with Flux Dev)
text_encoders 2 : HiDream CLIP - Distilled for Flux (Download) (471.71MB)

path : \ComfyUI\models\text_encoders\

2) Download my workflow for <Flux.1-krea-dev (nunchaku version)>

{20sec 1 photo}

https://civitai.com/models/1831687/flux1-krea-dev-nunchaku-my-20sec-workflow

-----------

Lora I use in this workflow

https://civitai.com/collections/11428250 (check my Flux Lora collection)


https://civitai.com/models/685874/flux-detailer
https://civitai.com/models/1166973/aesthetic-details
https://civitai.com/models/643886/flux-faetastic-details
https://civitai.com/models/1470162/midjourney-v7-meets-flux-illustrious
https://civitai.com/models/1371216/realanime

path : ....\ComfyUI\models\loras\

--- --- --- --- --- --- --- --- --- --- --- ---
advanced text_encoders are recommended to make it easier for you to create masterpieces

text_encoders 1 : t5xxl_fp8_e4m3fn_scaled  (same with Flux Dev)
text_encoders 2 : HiDream CLIP - Distilled for Flux (Download) (471.71MB) optional !!!
text_encoders 3 : clip_l
(You can use Flux Dev - text_encoders)
path : ....\ComfyUI\models\text_encoders\

前の画像
Aurora Tears - v1.0
次の画像
RouWei - v0.7 vpred
このモデルを使用

モデル詳細

モデルタイプ

Checkpoint

ベースモデル

Flux.1 D

モデルバージョン

v1.0

モデルハッシュ

c1dffa6bf3

作成者

BlackLabe188's avatar
BlackLabe188

ディスカッション

コメントを残すには log in してください。

モデルコレクション - Flux krea dev (nunchaku svdq-fp4) Base-Model

Close-up of two teal ceramic cups filled with cappuccino topped with heart-shaped foam, placed on a rustic wooden table beside a potted orange flower, with a softly blurred outdoor café background including warm string lights.
Checkpointモデル

Flux krea dev (nunchaku svdq-fp4) Base-Model - v1.0

短いハッシュ:
c1dffa6bf3

「Flux krea dev (nunchaku svdq-fp4) Base-Model - v1.0」による画像

Close-up of two teal ceramic cups filled with cappuccino topped with heart-shaped foam, placed on a rustic wooden table beside a potted orange flower, with a softly blurred outdoor café background including warm string lights.
Close-up black and white photo of bare feet standing on a bed of daisies with shallow depth of field, highlighting skin texture and flower petals.

基本モデル画像

Photorealistic scene of undead characters including zombies and skeletons walking through a spooky Halloween cemetery filled with glowing jack-o'-lantern pumpkins and desiccated trees in a dark, foggy atmosphere.

flux画像

A sultry steampunk heroine wearing bronze goggles on her forehead, dressed in a revealing mechanic outfit with a leather jacket, standing in an industrial workshop surrounded by intricate machinery.
A Windwaker style cartoon featuring a small boy standing at a fork in the road with a bright castle labeled 'Family, Friends, Happiness' on the left and a dark castle with flames and the word 'Flux' on the right.
A sweeping aerial view of a futuristic desert metropolis with towering bio-engineered structures featuring reflective glass and organic curves, set amidst sand dunes and ancient ruins with a winding geothermal channel.
Close-up of Itachi with pale skin, bright red eyes, and long dark hair wearing a headband with the Konoha symbol and a black cloak with red cloud patterns, surrounded by flying crows.
Young woman with short black hair wearing a tank top and shorts, sitting drunk against a green tiled wall on a concrete floor in an underground club, with empty beer bottles nearby.
A tired market vendor wearing a dark hoodie sits behind a cluttered counter in a dimly lit, dystopian setting with a hanging light bulb illuminating tools and supplies.
Delicate watercolor depiction of crystallized hoarfrost formations clinging to bare winter branches, featuring soft blue-white luminescence and a lavender-cerulean background.
パーカーを着た人物が、鮮やかな稲妻に支配された抽象的なシーンと相互作用し、渦巻くパターンと輝くオーブに囲まれています。

モデル画像

A confident girl with burgundy hair in greyscale stands under a bridge at night wearing a black crop top, checkered jacket, and denim pants.
Dynamic illustration of a girl with aqua hair in a high ponytail, orange eyes, red lips, dressed in a white cropped shirt and black pants, reaching hands forward against a white honeycomb background.
A girl with long auburn hair, eyes closed, wearing a denim jacket and black shirt stands in a wheat field during rain under a grey sky with falling autumn leaves.
Close-up portrait of an Asian girl with a pixie cut, wearing diamond earrings and a white tank top, illuminated by dappled sunlight and realistic lighting.
Young woman with black hair wearing a white floral dress holding a perfume bottle with closed eyes and sitting against a white background.
A model in a high fashion photo shoot wearing a geometric design dress featuring black, white, and red patterns, standing against a matching geometric patterned background.
Beautiful girl with black bob cut hair wearing retro floral dress and gold necklace, sitting inside a car during golden hour with soft film grain effect.
Stylish K-pop girl with orange short hair wearing a shiny purple bomber jacket and blue cargo pants posing on a neon-lit urban street with palm trees, pastel buildings, and a retro car during sunset.
Stable Diffusion AIを使用して作成された、赤いチェック柄スカートとオフショルダートップスを着た美しいカウガール。
詳細な周囲があるミニチュア列車機関車のハイパーリアリスティックな画像。