Download
1 variant available
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.
This LoRA captures a distinctive high-glam couture style defined by crystal embellishments, liquid shimmer textures, daring cutouts and body-contouring eveningwear silhouettes (inspired by Julien Macdonald). The model learned how to apply sparkling metallic surfaces, deep plunging constructions and provocative glamour styling to a wide variety of garments.
It works particularly well for red carpet fashion, high fashion editorial and runway eveningwear, but the style can also transfer surprisingly well to other glamorous or experimental fashion concepts.
The training set includes many different types of outfits and couture elements, for example:
crystal mesh evening gowns
shimmering metallic dresses with liquid-like sparkle
deep plunging necklines and dramatic chest framing
bold side cutouts and waist-revealing constructions
body-hugging cocktail dresses and evening gowns
embellished mini dresses and sculpted midi silhouettes
sheer illusion elements and sparkling surface textures
draped glamour dresses with gathered knot details
provocative red carpet styling
luxurious runway and editorial fashion looks
The LoRA focuses on materials, surface textures, silhouette language and glamour styling, not on specific identities or faces.
Because of this, the style can also transfer well to other fashion domains such as:
cocktail dresses
luxury nightlife looks
swimwear-inspired glamour concepts
sensual editorial fashion
futuristic eveningwear
experimental cutout fashion
This is, just like my other clothing LoRAs, not a "single outfit LoRA". Instead, I trained how fabric works, falls, looks and behaves and how much skin is exposed.
Would love if you post your creations here with it.
The LoRA was trained on the default flux1-dev model for maximum compatibility.
Dataset and training data:
94 images
10 steps per image
10 epochs
bucks with 1152px max size, no auto scaling
cosine scheduler with 0.2 warmup and 0.8 decay
Captioning was done with OpenAI
alpha == dim: 32
If you use it with other loras, for example a character lora, try to lower the weight - I had good results at around 0.4-0.5.
As always: I did not polish any of the images in the showcase, they all came out like this. I did 2 images per prompt and picked the better looking one.