LoRA model for Flux: Lamborghini Centenario 2017 Limited Edition

The neural model Lamborghini_Centenario_2017_Limited_Edition_360 is a LoRA (Low-Rank Adaptation) developed based on the innovative FLUX.1-schnell technology, a proprietary variant of Flex.1 by ostris. This model was trained on a local computer using fluxgym and is designed for image generation, demonstrating high accuracy and realism.

Trigger words: You should use the phrase "Lamborghini C 2017" to trigger the image generation.

When generating images, use commands to change angles.

These commands were entered as text triggers into the dataset during the neural network training process:

(Front view. Left view.)

(Front view. Right view.)

(Rear view. Right view.)

(Rear view. Left view.)

(Bottom view. Left view.)

(Bottom view. Right view.)

(Top view. Left view.)

(Top view. Right view.)

(Top view. Left view. Rear view.)

(Top view. Right view. Rear view.)

(Top view. Right view. Front view.)

(Top view. Left view. Front view.)

(In flight)

(The doors are open)

Key Features and Technical Details:

Training Technology: The model is based on FLUX.1-schnell, which ensures efficient and high-quality training.

License: The model is distributed under the Apache License Version 2.0, allowing its free use and distribution in accordance with the license terms. License link: https://huggingface.co/ostris/Flex.1-alpha/blob/main/LICENSE.txt.

Generation Accuracy: LoRA achieves up to 98% similarity in generated images to the target style or object, significantly outperforming generation without LoRA (50-60%).

Dataset: The neural model was exclusively trained on a 100% copyrighted and legally synthetic dataset.

Training Software: The training was performed using fluxgym (https://github.com/cocktailpeanut/fluxgym).

Training Parameters from dataset.toml and train.txt:

resolution: 1440

batch_size: 1

keep_tokens: 1

class_tokens: 'Lamborghini C 2017'

num_repeats: 10

learning_rate: 8e-4

max_train_epochs: 4

save_every_n_epochs: 1

discrete_flow_shift: 3.1582

guidance_scale: 1

loss_type: l2

Images for Data Set: 14

Instructions for Image Generation:

To activate image generation, you must use the trigger words: Lamborghini C 2017. The weights for this model are available in Safetensors format, making it compatible with popular image generation software such as ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, Forge, and others.