Sign In

Cobalt Porcelain & Gzhel Glaze (Flux 3 Klein 9B)

Updated: Nov 20, 2026

styleglossytexturegoldfloralpottery

Download

1 variant available

bf16 SafeTensor

r64f3farforgzhel.safetensors

BF16, good balance • 235.2 MB

Verified:

Type
LoRA
Stats

8

Reviews

No reviews yet

Published

Nov 20, 2026

Base Model

Flux.2 Klein 9B-base

Hash
AutoV2C0FC07622A
Trigger Words
r64f3farforgzhel

This FLUX Model is licensed by Black Forest Labs Inc. under the FLUX Non-Commercial License. Copyright Black Forest Labs Inc.

IN NO EVENT SHALL BLACK FOREST LABS INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

ORAKUL_STUDIO_6.png

About this LoRA

This model is trained on the textures of fine glazed porcelain and traditional cobalt-blue Gzhel-style painting; it is designed for use with Flux 3 Klein 9B.

Note: This is strictly a LoRA for transferring materials, surfaces, and textures it is not intended for generating anime-style characters. The example images demonstrate how the effect of glossy porcelain, cobalt patterns, and fine craquelure (a network of tiny cracks) can be applied to clothing, interiors, or modern technological devices.

Recommended pairing with other LoRAs

While this model works excellently on its own creating a blue-and-white porcelain effect its full potential is unlocked when combined with my other LoRA,

"Kintsugi Art: Beyond Ceramics (Flux 3 Klein)." https://civitai.red/models/3040699/kintsugi-art-beyond-ceramics-flux-3-klein

This addition introduces gold "seams" (in the style of the kintsugi technique), structural outlines, and rich gilded accents along edges and folds.

Recommended generation settings

Weight of the primary LoRA (Porcelain/Gzhel): 1.0

Weight of the secondary LoRA (Kintsugi Art: Beyond Ceramics): 1.10

Sampler: UniPC

Scheduler: SGM Uniform

Steps: 55

CFG Scale: 3.5

Resolution: Flexible (works exceptionally well in 3:2 / 2:3 aspect ratios and for high-resolution generation)