Sign In

FLUX.2-dev (32B) Van Gogh Style (Rank 2048-12-billion parameters.)

Download

0 variants available

No files available

Type
LoRA
Stats

5

Reviews
Published

Sep 21, 2026

Base Model

Flux.2 D

Hash
AutoV2
A6F7B02626
Trigger Words
r2048f2dvangog
default creator card background decoration
Uploads - 42

42

Followers - 92

92

Likes - 231

231

The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] 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.

Снимок экрана 2026-09-21 220033.png

A flagship release utilizing the maximum weight capacity. The model was trained at an uncompromising rank of 2048, enabling it to capture not just basic stylistic attributes, but also complex color logic, distinctive painterly underpainting (including olive-green skin undertones), and the authentic physical qualities of the somber Nuenen-era aesthetic.

Technical Specifications

Base Model: FLUX.2-dev (32B parameters)

LoRA Rank: 2048

Operating Weight (Strength): 1.0

Dataset Size: ~850 carefully selected and manually prepared reference works (representing nearly half of the artist's entire creative legacy)

Recommended Generation Parameters

Sampler: DPMPP 3M SDE GPU

Scheduler: Linear Quadratic

Steps: 40

CFG Scale / Guidance: 3.5

Release Notes:

No specific constraints or complex pipelines are required; the model reliably maintains geometry and material physics at the standard weight of 1.0.

A distilled, lightweight version of this model (Rank 128) will be released separately later for quick testing and more efficient memory usage.

You can also test the model at earlier training steps by following the Hugging Face link.

OrakulStorm/Master-Weights-Experimental-SencneS · Hugging Face