Wolverina v3

LORA
Original


Updated:

Parameter Settings

Network Module

  • LoRA

  • Use Base Model: FLUX - Dev fp32

  • Trigger Words: fmlwol, femwolv costume

Image Processing Parameters

  • Repeat: 10

  • Epoch: 7

  • Save Every N Epochs: 1

Training Parameters

  • Seed: -

  • Clip Skip: 2

  • Text Encoder Learning Rate: -

  • Unet Learning Rate: 0.0004

  • LR Scheduler: cosine

  • Optimizer: AdamW

  • Network Dim: 16

  • Network Alpha: 2

  • Gradient Accumulation Steps: 1

Label Parameters

  • Shuffle Caption: -

  • Keep n Tokens: -

Advanced Parameters

  • Noise Offset: 0.2

  • Multires Noise Discount: 0.35

  • Multires Noise Iterations: 12

  • Conv Dim: 128

  • Conv Alpha: 32

  • Batch Size: -

Sample Image Settings

  • Prompt: fmlwol, femwolv costume, a beautiful dark-haired woman wearing a femwolv costume, she's in an urban setting, heroic pose, heroic posing, ultra quality, ultra detailed textures, ultra realistic

  • Sampler: euler

Version Detail

Trained by Tensor
FLUX.1
5

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.