alexgenovese / train-sdxl-lora

Train on RealVisXL 4.0 (Realistic Vision XL 4) | Mixed precision bf16 any LoRA

  • Public
  • 598 runs
  • A100 (80GB)
  • GitHub
Iterate in playground
  • Prediction

    alexgenovese/train-sdxl-lora:533e1248263c06db92aea251ca69c3115f3ffbd19c86346b46e52eda14e8fd11
    ID
    rsan62rbf65msxaftuoqcuvvnm
    Status
    Succeeded
    Source
    Web
    Hardware
    A100 (40GB)
    Total duration
    Created
    by @alexgenovese

    Input

    seed
    82
    ti_lr
    0.0001
    is_lora
    lora_lr
    0.0004
    verbose
    lora_rank
    32
    resolution
    1024
    class_token
    blazer
    lr_scheduler
    constant
    optimization
    AdamW
    token_string
    siduhc
    caption_prefix
    a photo of siduhc blazer
    lora_rank_alpha
    32
    lr_warmup_steps
    0
    num_train_epochs
    100
    train_batch_size
    2
    unet_learning_rate
    0.0001
    checkpointing_steps
    999999
    clipseg_temperature
    1
    input_images_filetype
    infer
    crop_based_on_salience
    use_face_detection_instead

    Output

    Generated in

Want to make some of these yourself?

Run this model