{
  "model_id": "runwayml/stable-diffusion-v1-5",
  "output_dir": "/kaggle/working/lora_output",
  "hf_repo_id": "huydev0000/text_to_image_finetune",
  "lora_rank": 32,
  "lora_alpha": 64,
  "lora_dropout": 0.05,
  "target_modules": [
    "to_k",
    "to_q",
    "to_v",
    "to_out.0",
    "ff.net.0.proj",
    "ff.net.2"
  ],
  "resolution": 512,
  "train_batch_size": 4,
  "gradient_accum": 2,
  "learning_rate": 0.0002,
  "max_train_steps": 4000,
  "save_steps": 2000,
  "lr_scheduler": "cosine",
  "warmup_steps": 500,
  "mixed_precision": "fp16",
  "seed": 42,
  "snr_gamma": 5.0,
  "cfg_drop_prob": 0.1,
  "resume_from": ""
}

Usage

python

from diffusers import StableDiffusionPipeline
from peft import PeftModel
import torch

pipe = StableDiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16
)
pipe.unet = PeftModel.from_pretrained(pipe.unet, "your-username/your-lora")
pipe.to("cuda")

image = pipe("your prompt here").images[0]