Masha K v2 - root - 8

Masha K v2 - root

LORA
Original


Updated:

📂 Masha K v2 – Root

⚙️ Parameter Settings

🧩 Network Module

  • Type: LoRA

  • Base Model: FLUX – Dev fp32

  • Trigger words: maxxa

🖼️ Image Processing

  • Repeat: 8

  • Epochs: 8

  • Save Every N Epochs: 1

🎛️ Training Parameters

  • Seed: 42

  • Clip Skip: 1

  • Text Encoder LR: 0.000015

  • Unet/DiT LR: 0.000085

  • LR Scheduler: constant

  • Optimizer: AdamW

  • Network Dim: 128

  • Network Alpha: 110

  • Gradient Accumulation Steps: 4

🏷️ Label Parameters

  • Shuffle caption:

  • Keep n tokens:

🔬 Advanced Parameters

  • Noise offset: 0.0082

  • Multires noise discount: 0.095

  • Multires noise iterations: 2

  • conv_dim: 128

  • conv_alpha: 120

  • Batch Size:

📸 Sample Image Settings

Prompt:

maxxa, three-quarter body analog-style photograph, frontal view, shot by sx-70. A blonde woman, fit, stands confidently in a forest with ethereal atmosphere. Her body softly accentuated by directional lighting. Her long wavy hair cascades past her shoulders with strand realism. Her blue eyes are enhanced with mascara and subtle eyeliner, paired with red lips, a small nose, and a calm, focused expression. She is wearing a pink top, red leather skirt and red stockings. Her posture is upright and poised, one hand resting on her waist, the other hand on her thigh. Her legs are crossed. She is looking at the viewer, daring expression. Validator-grade skin texture includes visible pores, tonal variation, and soft blemish scattering across her face, neck, arms, and legs.

  • Sampler: dpmpp_2m

Version Detail

Trained by Tensor
FLUX.1
8

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