Tensor.Art
Create

Hires- Jia lissa

LORA
Original

Updated:

11
Best Version
13

Image Processing Parameters

Training Parameters

Label Parameters

Advanced Parameters

Sample Image Settings

Network ModuleLoRAUse Base ModelFLUX - Dev fp32Trigger wordsjiav3Repeat2Epoch14Save Every N Epochs1Seed-Clip Skip1Text Encoder learning rate0.00005Unet learning rate0.0004LR Schedulercosine_with_restartsOptimizerAdamW8bitNetwork Dim64Network Alpha8Gradient Accumulation Steps1Shuffle caption-Keep n tokens-Noise offset0.05Multires noise discount0.2Multires noise iterations10conv_dim32conv_alpha4Batch Size-Promptjiav3,

Version Detail

Trained by Tensor
FLUX.1
14
### **Image Processing Parameters** - Sample Image Settings ### **Training Parameters** - Repeat: 2 - Epoch: 14 - Save Every N Epochs: 1 - Seed-Clip Skip: 1 - Batch Size ### **Label Parameters** - Shuffle Caption - Keep N Tokens ### **Advanced Parameters** - Noise Offset: 0.05 - Multires Noise Discount: 0.2 - Multires Noise Iterations: 10 - Conv Dim: 32 - Conv Alpha: 4 ### **Network Module** - **LoRA** - Use Base Model: FLUX - Dev fp32 - Trigger Words: jiav3 ### **Learning Rate & Optimization** - Text Encoder Learning Rate: 0.00005 - Unet Learning Rate: 0.0004 - LR Scheduler: Cosine_with_restarts - Optimizer: AdamW8bit - Network Dim: 64 - Network Alpha: 8 - Gradient Accumulation Steps: 1

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.