Official

lucataco / train-text-to-image-lora

Huggingface Diffusers: SDv1.4/1.5/2.0/2.1 finetuner

  • Public
  • 16 runs
  • L40S
  • GitHub
  • License
  • Prediction

    lucataco/train-text-to-image-lora:aa769732ccfc922fb77ec36c1bd3680208394f1770402db52681fc8556e9356a
    ID
    c9e78t8wehrgp0cgzc6s9tnb44
    Status
    Succeeded
    Source
    Web
    Hardware
    A40 (Large)
    Total duration
    Created

    Input

    dataset
    lambdalabs/naruto-blip-captions
    base_model
    runwayml/stable-diffusion-v1-5
    resolution
    512
    hub_model_id
    naruto-lora
    lr_scheduler
    cosine
    learning_rate
    0.0001
    max_grad_norm
    1
    max_train_steps
    1000
    num_train_epochs
    100
    train_batch_size
    1
    validation_prompt
    A naruto with blue eyes.
    dataloader_num_workers
    8
    gradient_accumulation_steps
    4

    Output

    Generated in

Want to make some of these yourself?

Run this model