LoRA Training for SD 1.x/2.x

Overview

train_network.py is the core LoRA training script for Stable Diffusion v1.x and v2.x models. It supports LoRA-LierLa (the default), LoRA-C3Lier (with 3×3 convolution layers), and a range of optimizers and learning rate schedulers.

For SDXL, FLUX.1, or SD3 models, use the dedicated scripts described in their respective pages. This page covers SD 1.x and 2.x only.

Prerequisites

The sd-scripts repository cloned and the Python environment set up.
A prepared dataset and a TOML dataset config file.
A Stable Diffusion v1.x or v2.x .safetensors or .ckpt base model.

Training command

Below is a complete example that you can adapt to your setup. Use \ for line continuation on Linux/macOS or ^ on Windows.

accelerate launch --num_cpu_threads_per_process 1 train_network.py \
  --pretrained_model_name_or_path="/path/to/model.safetensors" \
  --dataset_config="my_dataset_config.toml" \
  --output_dir="./output" \
  --output_name="my_lora" \
  --save_model_as=safetensors \
  --network_module=networks.lora \
  --network_dim=16 \
  --network_alpha=8 \
  --learning_rate=1e-4 \
  --unet_lr=1e-4 \
  --text_encoder_lr=1e-5 \
  --optimizer_type="AdamW8bit" \
  --lr_scheduler="cosine_with_restarts" \
  --lr_warmup_steps=100 \
  --sdpa \
  --max_train_epochs=10 \
  --save_every_n_epochs=1 \
  --mixed_precision="fp16" \
  --gradient_checkpointing

Write the command on a single line or use the appropriate line-continuation character for your shell.

Key arguments

Required arguments

string

required

Path to the base Stable Diffusion model. Accepts a local .ckpt or .safetensors file, a Diffusers-format directory, or a Hugging Face Hub model ID such as "stabilityai/stable-diffusion-2-1-base".

string

required

Path to the .toml file that describes the training dataset. See the dataset configuration guide for the full format.

string

required

Directory where trained LoRA models, sample images, and logs are saved.

string

required

Base filename for the saved LoRA (without extension). The final file will be <output_name>.safetensors.

string

required

Network type to train. Use networks.lora for standard LoRA. Use networks.dylora for DyLoRA.

integer

required

LoRA rank (dimension). Higher values increase expressiveness and file size. Common values: 4, 8, 16, 32, 64, 128.

Network parameters

number

default:"1"

Alpha value that scales the LoRA output. Setting this equal to network_dim matches older behavior. A value of half network_dim is a common default.

number

Dropout rate (0.0–1.0) applied inside LoRA modules. Can help reduce overfitting. Omit to disable.

string[]

Additional key=value arguments passed to the network module. For LoRA-C3Lier (3×3 convolution layers), add "conv_dim=4" "conv_alpha=1".

Saving

string

default:"safetensors"

File format for the saved model. Options: safetensors (recommended), ckpt, pt.

integer

Save a checkpoint every N epochs. If omitted, only the final model is saved.

integer

Save a checkpoint every N steps. Can be used alongside --save_every_n_epochs.

Learning rate

number

default:"1e-4"

Global learning rate used when --unet_lr and --text_encoder_lr are not specified.

number

Learning rate for LoRA modules inside the U-Net. Falls back to --learning_rate when omitted.

number

Learning rate for LoRA modules inside the text encoder. Recommended to be lower than the U-Net rate (e.g., 1e-5).

string

default:"constant"

Learning rate schedule. Options: constant, cosine, linear, constant_with_warmup, cosine_with_restarts, polynomial.

integer

Number of steps over which the learning rate ramps up from zero to the target value at the start of training.

Training duration

integer

Number of epochs to train. When set, --max_train_steps is ignored.

integer

Total number of training steps. Used only when --max_train_epochs is not set.

Optimizer

string

default:"AdamW8bit"

Optimizer to use. Options include AdamW8bit (requires bitsandbytes), AdamW, Lion (requires lion-pytorch), Adafactor, DAdaptation, Prodigy, schedulefree.

Memory and speed

string

default:"no"

Mixed precision training mode. Use fp16 or bf16 to reduce VRAM usage and speed up training. Requires GPU support.

boolean

Enables gradient checkpointing to reduce VRAM at the cost of slightly slower training.

boolean

Uses PyTorch’s Scaled Dot-Product Attention. Reduces memory and can improve speed.

integer

default:"1"

Accumulate gradients over N steps before updating weights. Effectively multiplies the batch size without increasing VRAM.

SD 2.x specific flags

When training on Stable Diffusion v2.x models, add the following flags:

SD 2.x (512px, epsilon)
SD 2.x (768px, v-prediction)

--v2

Use --v2 for v2.x models that use epsilon (noise) parameterization, such as stable-diffusion-2-base.

--v2 \
--v_parameterization

Add --v_parameterization for v2.x models trained with v-prediction, such as stable-diffusion-2-1 at 768px.

Omitting --v2 when training on a v2.x model will cause incorrect behavior because the text encoder architecture differs from v1.x.

Conv2d LoRA (LoRA-C3Lier)

By default, LoRA targets only Linear layers and 1×1 Conv2d layers. To also apply LoRA to 3×3 Conv2d layers (LoRA-C3Lier), pass conv_dim in --network_args:

--network_args "conv_dim=4" "conv_alpha=1"

This produces slightly larger LoRA files and may improve quality for style training, at the cost of overfitting risk with small datasets.

Monitoring training

If you specify --logging_dir, you can visualize the training loss and learning rate with TensorBoard:

tensorboard --logdir ./logs

Using the trained LoRA

When training completes, a .safetensors file is saved to your --output_dir. You can load it in:

AUTOMATIC1111 stable-diffusion-webui — place in models/Lora/ and reference with <lora:my_lora:1> in your prompt.
ComfyUI — use a LoraLoader node pointing to the file.

Getting Started

Dataset Preparation

LoRA Training

Fine-tuning & Other Methods

Inference & Utilities

LoRA Training for SD 1.x/2.x

Overview

Prerequisites

Training command

Key arguments

Required arguments

Network parameters

Saving

Learning rate

Training duration

Optimizer

Memory and speed

SD 2.x specific flags

Conv2d LoRA (LoRA-C3Lier)

Monitoring training

Using the trained LoRA

​Overview

​Prerequisites

​Training command

​Key arguments

​Required arguments

​Network parameters

​Saving

​Learning rate

​Training duration

​Optimizer

​Memory and speed

​SD 2.x specific flags

​Conv2d LoRA (LoRA-C3Lier)

​Monitoring training

​Using the trained LoRA

Overview

Prerequisites

Training command

Key arguments

Required arguments

Network parameters

Saving

Learning rate

Training duration

Optimizer

Memory and speed

SD 2.x specific flags

Conv2d LoRA (LoRA-C3Lier)

Monitoring training

Using the trained LoRA