Industrial GSv3 - 2nd

LORA
Original


Updated:

Parameter Settings

Network Module

  • LoRA

  • Use Base Model: FLUX - Dev fp32

  • Trigger Words: 1ndustr14lvl2

Image Processing Parameters

  • Repeat: 1

  • Epochs: 20

  • Save Every N Epochs: 1

Training Parameters

  • Seed: -

  • Clip Skip: -

  • Text Encoder Learning Rate: 0.0001

  • Unet Learning Rate: 0.0001

  • LR Scheduler: constant

  • Optimizer: AdaFactor

  • Network Dim: 128

  • Network Alpha: 128

  • Gradient Accumulation Steps: 1

Label Parameters

  • Shuffle Caption: -

  • Keep n Tokens: -

Advanced Parameters

  • Noise Offset: -

  • Multires Noise Discount: 0.3

  • Multires Noise Iterations: -

  • conv_dim: 1

  • conv_alpha: 1

  • Batch Size: -

Sample Image Settings

  • Prompt: 1ndustr14lvl2, ultra quality, ultra detailed, ultra realistic, cinematic. A beautiful American woman in a gothic industrial outfit stands on a city street at night, surrounded by neon lights. She has long black hair with red highlights in dreads and wears a red and black plaid dress with puffy sleeves and a short skirt. Her thigh-high socks are black with red stripes, and she carries a large black handbag. The background features a dance club with neon lights and partygoers. The image is a high-resolution photograph with a shallow depth of field, focusing on the subject while the background is softly blurred. The lighting is artificial, casting a cool glow on the scene.

  • Sampler: euler

Version Detail

Trained by Tensor
FLUX.1
19

Project Permissions

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Related Posts

Describe the image you want to generate, then press Enter to send.