Diffus
Get started
models/Flux krea dev (nunchaku svdq-fp4) Base-Model - v1.0

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

BlackLabe188
|
12/18/2025
|
5:19:55 AM
| Discussion|
0
Two teal ceramic cups filled with cappuccino featuring heart-shaped foam sitting on a rustic wooden table next to a potted plant with an orange flower, blurred outdoor café and warm string lights in the background.
Close-up black and white photo of bare feet standing in a field of daisies with shallow depth of field emphasizing the feet and flowers in soft natural light.

Recommended Parameters

samplers

dpmpp_2m_sde_gpu

steps

20 - 30

cfg

5 - 7

clip skip

1

resolution

512x512

Tips

Minimum VRAM requirement is about 6 GB (e.g. 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 is 32 GB.

Use advanced text encoders like t5xxl_fp8_e4m3fn_scaled and clip_l for easier creation of masterpieces.

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

Ready integration with Diffusers and ComfyUI for seamless workflow.

Recommended LoRA collections and models for enhanced detail: flux-detailer, aesthetic-details, flux-faetastic-details, midjourney-v7-meets-flux-illustrious, realanime.

Version Highlights

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

  • Minimum VRAM requirement 6 GB +

  • System-ram 16 GB +

Creator Sponsors

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 : clip_l (you can just use this to replace HiDream)
text_encoders 3 : Long CLIP - Distilled for Flux (Download) (471.71MB) optional !!!

path : \ComfyUI\models\text_encoders\

2) Download my workflow for <Flux.1-krea-dev (nunchaku version)> {20sec 1 photo}

Workflow v1 2025.08.03
https://civitai.com/models/1831687/flux1-krea-dev-nunchaku-my-20sec-workflow

Workflow v2 2025.08.13
https://civitai.com/models/1831687?modelVersionId=2107254

workflow name : 1-nunchaku-flux.1-dev(T2I) 10Lora-Pro.json v2.0

-----------

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\

Previous
Lois Lane the best version - 100
Next
Massive Cows LoRA - v1.0
Use this model

Model Details

Model type

Checkpoint

Base model

Flux.1 D

Model version

v1.0

Model hash

c1dffa6bf3

Creator

BlackLabe188's avatar
BlackLabe188

Discussion

Please log in to leave a comment.

Model Collection - Flux krea dev (nunchaku svdq-fp4) Base-Model

Two teal ceramic cups filled with cappuccino featuring heart-shaped foam sitting on a rustic wooden table next to a potted plant with an orange flower, blurred outdoor café and warm string lights in the background.
CheckpointMODELS

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

Short Hash:
c1dffa6bf3

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

Two teal ceramic cups filled with cappuccino featuring heart-shaped foam sitting on a rustic wooden table next to a potted plant with an orange flower, blurred outdoor café and warm string lights in the background.
Close-up black and white photo of bare feet standing in a field of daisies with shallow depth of field emphasizing the feet and flowers in soft natural light.

base model Images

Photorealistic scene of undead characters including zombies and skeletons walking through a spooky cemetery illuminated by glowing jack-o'-lanterns under a dark, ominous sky.

flux Images

A dark, eerie face composed of white ASCII characters on a black background, with glowing eyes and a highly detailed texture.
Cartoony scene in Windwaker style showing a small boy standing at a fork in the road with two castles: a bright one labeled family, friends, happiness; and a dark fiery one labeled Flux.
Stylized forest scene with tall trees, autumn foliage, bright light rays shining through, and a clear water surface reflecting the scenery.
A complex steampunk industrial structure with rusted metal, metal ladders, and warm yellow lights, towering above a dense foggy landscape.
Side profile of a female android with light beige weathered skin and intricate exposed mechanical parts showing gears and circuits, against a muted dark background.
Anime-style close-up portrait of a female collector wearing spectacles, holding a glowing orb with both hands in an attic filled with old books and artifacts.
A bright mountainous landscape with a turquoise river flowing through a rocky canyon, snow-capped peaks in the background, and green pine trees on cliffs. Underwater, a shadowy rocky canyon riverbed is visible.
Anime-style portrait of an elegant woman with a short bob hairstyle wearing a black top, standing in warm ambient lighting with soft shadows and a golden drink on the table.
Orange tabby cat wearing a tattered green cloak and floppy hat, singing seriously while holding a rustic wooden lute, illuminated by soft lighting against a dark background.
A person in a hoodie interacts with an abstract scene dominated by a vibrant lightning bolt, surrounded by swirling patterns and glowing orbs.

model Images

A girl with auburn windblown hair and closed eyes stands in a rainy wheat field wearing a wet denim jacket over a black shirt under a cloudy grey sky with floating autumn leaves.
Model wearing a red and white striped leather jacket open to reveal her chest, standing in front of a brightly lit carousel at night in a circus setting.
Cinematic fashion portrait of a model captured with a film camera, featuring selective focus and haute couture styling.
Portrait of an Asian girl with a pixie cut and black hair, wearing diamond earrings and a white tank top, illuminated by soft sunlight through curtains.
A young woman with very long platinum hair wearing a black satin dress with a thigh-high slit, standing on a city street at night with bokeh lights in the background.
Portrait of a woman in a dark urban environment at night wearing an orange jacket with a softly blurred background.
Young woman with black hair and closed eyes wearing a white floral dress, holding a perfume bottle against a white background.
Close-up analog style photo of a beautiful girl with black bob haircut sitting in a car at golden hour, wearing retro floral dress and a necklace, with soft focus and warm light.
K-pop styled girl with short orange hair wearing a shiny purple bomber jacket and blue cargo pants, standing on a pastel-colored urban street with neon signs and palm trees under a clear sky.
A beautiful cowgirl in a red plaid skirt and off-shoulder top, created using Stable Diffusion AI.