Tie-Dye Batik LoRA for Stable Diffusion XL

This is a LoRA model trained on tie-dye batik patterns, specifically for Stable Diffusion XL (SDXL). It can be used to generate tie-dye batik style textures.

Model Details

  • Base Model: Stable Diffusion XL (SDXL) 1.0
  • Training Parameters:
    • Resolution: 512x512
    • Training Steps: 500
    • Learning Rate: 1e-04
    • Batch Size: 1
    • Gradient Accumulation Steps: 4
    • Mixed Precision: fp16
    • VAE: madebyollin/sdxl-vae-fp16-fix

Training

This model was trained on a custom dataset of tie-dye batik texture images with captions.

Check the official documentation on fine-tuning: https://huggingface.co/docs/diffusers/main/en/training/lora

Example Images

image/png

Usage

This LoRA should be used with Stable Diffusion XL 1.0.

Recommended prompt structure: [trigger word], [overall shape], [pattern description], [colors]

Example prompt: tie dye batik texture, spiral, radiating from center, green color, orange color, white color

Recommended weight: 0.7-1.0

Inference

Notebook on Kaggle: https://www.kaggle.com/code/pabasar/tie-dye-batik-diffusion

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW

Model tree for pabasar/tie-dye-batik-lora

Adapter
(9724)
this model