Download
0 variants available
No files available
50 1 2 3 4 5 6 7 8 9
No reviews yet
Sep 21, 2026

420 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
920 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
2310 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
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.
Parameters (technical specifications and generation settings) Base Model:
Flux 2 (32B) Architecture: LoRA Rank 1792 / Alpha 1792 (uncompressed high-rank adapter) LoRA Weight: 1.0 Steps: 50
CFG / Guidance: 3.5
Sampler: dpmpp_3m_sde_gpu
Scheduler: linear_quadratic
Description:
Orakul Van Gogh Full Rank r1792. The flagship model from the "Uncompressed High-Rank Stack" series, recreating the authentic physics of impasto oil painting, palette-knife stroke textures, and Vincent van Gogh’s color palette, based on Flux 2 (32B). Key features of r1792: Preservation of individual facial features: thanks to the high capacity of the r1792 matrix, the model does not sacrifice facial anatomy for the sake of style; it transfers original proportions, eye shapes, and facial features onto the canvas without the need for text-based adjustments (feature retention). Deep oil painting texture: rich, tangible impasto, voluminous brushstrokes, and historically accurate pigments (ranging from dark Dutch ochre to the blue-gold tones of Arles). Autonomous context generation: even with a minimal prompt, the model independently constructs an interior or landscape characteristic of that era.
Note: For users with limited VRAM, a distilled version of the model will be released separately (Distilled Edition: compression from rank 1792 to a lightweight rank 128).

