LoRA model for Flux: Tesla Model 3 Electric Race Car

Here is a technical description of the LoRA neural model: Tesla_Model_3_Electric_Race_Car_360.

This LoRA neural model was trained using the FLUX.1-schnell technology, which is an original variation of Flex.1 by ostris. The model demonstrates high generation accuracy, achieving up to 98% similarity with the source material, compared to 50-60% when generating without LoRA. The model was trained exclusively on a 100% copyrighted and legal synthetic dataset. The fluxgym software was used for training.

Trigger Words: You must use the phrase 'tesla racing car' to activate 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)

Licensing:

The model is distributed under the Apache License Version 2.0.

License link: https://huggingface.co/ostris/Flex.1-alpha/blob/main/LICENSE.txt.

Training Parameters:

Resolution: 1440

Batch size: 1

Keep tokens: 1

Class tokens: 'tesla racing car'

Number of repeats: 10

Learning rate: 8e−4

Max training epochs: 8

Save every N epochs: 4

Discrete flow shift: 3.1582

Guidance scale: 1

Loss type: l2

Network dimension: 100

Sample every N steps: 50

Number of images in the dataset: 13.

Brief Usage Instructions:

To generate images using this LoRA neural model, you can download it and use it with platforms such as ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, Forge, etc.. The weights for this model are available in Safetensors format.