d4zzl1ngs v1

LORA
Original


Updated:

Parameter Settings

Network Module

  • Type: LoRA

  • Base Model: FLUX - Dev fp32

  • Trigger Words: d4zzl1ngs

Image Processing Parameters

  • Repeat: 2

  • Epochs: 9

  • Save Every N Epochs: 1

Training Parameters

  • Seed: -

  • Clip Skip: 1

  • Text Encoder Learning Rate: -

  • Unet Learning Rate: 0.00005

  • LR Scheduler: Cosine

  • Optimizer: AdamW

  • Network Dim: 128

  • Network Alpha: 32

  • 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: 32

  • Conv Alpha: 2

  • Batch Size: -

Sample Image Settings

  • Prompt: d4zzl1ngs, cinematic, cinematic lighting. A beautiful red-haired woman wearing a tight pink bodysuit, with flowing hair in windy rooftop weather. She poses for the viewer during a photo shoot, holding a transparent plastic umbrella in her hands. She's in an urban setting with background buildings, the city at night, rainy weather, illuminated—old photography, analog photo, old imagery, 35mm, ultra quality, ultra realistic, ultra detailed.

  • Sampler: Euler

1

Version Detail

Trained by Tensor
FLUX.1
7

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