Skip to content

Latest commit

 

History

History
228 lines (157 loc) · 6.95 KB

SIGMA.md

File metadata and controls

228 lines (157 loc) · 6.95 KB
Raw

PixArt Sigma Quickstart

In this example, we'll be training a PixArt Sigma model using the SimpleTuner toolkit and will be using the full model type, as it being a smaller model will likely fit in VRAM.

Prerequisites

Make sure that you have python installed; SimpleTuner does well with 3.10 or 3.11. Python 3.12 should not be used.

You can check this by running:

python --version

If you don't have python 3.11 installed on Ubuntu, you can try the following:

apt -y install python3.11 python3.11-venv

Container image dependencies

For Vast, RunPod, and TensorDock (among others), the following will work on a CUDA 12.2-12.4 image:

apt -y install nvidia-cuda-toolkit libgl1-mesa-glx

If libgl1-mesa-glx is not found, you might need to use libgl1-mesa-dri instead. Your mileage may vary.

Installation

Clone the SimpleTuner repository and set up the python venv:

git clone --branch=release https://github.com/bghira/SimpleTuner.git

cd SimpleTuner

python -m venv .venv

source .venv/bin/activate

pip install -U poetry pip

# Necessary on some systems to prevent it from deciding it knows better than us.
poetry config virtualenvs.create false

Depending on your system, you will run one of 3 commands:

# MacOS
poetry install -C install/apple

# Linux
poetry install

# Linux with ROCM
poetry install -C install/rocm

AMD ROCm follow-up steps

The following must be executed for an AMD MI300X to be useable:

apt install amd-smi-lib
pushd /opt/rocm/share/amd_smi
python3 -m pip install --upgrade pip
python3 -m pip install .
popd

Removing DeepSpeed & Bits n Bytes

These two dependencies cause numerous issues for container hosts such as RunPod and Vast.

To remove them after poetry has installed them, run the following command in the same terminal:

pip uninstall -y deepspeed bitsandbytes

Setting up the environment

To run SimpleTuner, you will need to set up a configuration file, the dataset and model directories, and a dataloader configuration file.

Configuration file

An experimental script, configure.py, may allow you to entirely skip this section through an interactive step-by-step configuration. It contains some safety features that help avoid common pitfalls.

Note: This doesn't configure your dataloader. You will still have to do that manually, later.

To run it:

python configure.py

⚠️ For users located in countries where Hugging Face Hub is not readily accessible, you should add HF_ENDPOINT=https://hf-mirror.com to your ~/.bashrc or ~/.zshrc depending on which $SHELL your system uses.

If you prefer to manually configure:

Copy config/config.json.example to config/config.json:

cp config/config.json.example config/config.json

There, you will need to modify the following variables:

{
  "model_type": "full",
  "use_bitfit": false,
  "pretrained_model_name_or_path": "pixart-alpha/pixart-sigma-xl-2-1024-ms",
  "model_family": "pixart_sigma",
  "output_dir": "/home/user/output/models",
  "validation_resolution": "1024x1024,1280x768",
  "validation_guidance": 3.5
}
  • pretrained_model_name_or_path - Set this to PixArt-alpha/PixArt-Sigma-XL-2-1024-MS.
  • MODEL_TYPE - Set this to full.
  • USE_BITFIT - Set this to false.
  • MODEL_FAMILY - Set this to pixart_sigma.
  • OUTPUT_DIR - Set this to the directory where you want to store your checkpoints and validation images. It's recommended to use a full path here.
  • VALIDATION_RESOLUTION - As PixArt Sigma comes in a 1024px or 2048xp model format, you should carefully set this to 1024x1024 for this example.
    • Additionally, PixArt was fine-tuned on multi-aspect buckets, and other resolutions may be specified using commas to separate them: 1024x1024,1280x768
  • VALIDATION_GUIDANCE - PixArt benefits from a very-low value. Set this between 3.6 to 4.4.

There are a few more if using a Mac M-series machine:

  • mixed_precision should be set to no.

Dataset considerations

It's crucial to have a substantial dataset to train your model on. There are limitations on the dataset size, and you will need to ensure that your dataset is large enough to train your model effectively. Note that the bare minimum dataset size is TRAIN_BATCH_SIZE * GRADIENT_ACCUMULATION_STEPS. The dataset will not be discoverable by the trainer if it is too small.

Depending on the dataset you have, you will need to set up your dataset directory and dataloader configuration file differently. In this example, we will be using pseudo-camera-10k as the dataset.

In your /home/user/simpletuner/config directory, create a multidatabackend.json:

[
  {
    "id": "pseudo-camera-10k-pixart",
    "type": "local",
    "crop": true,
    "crop_aspect": "square",
    "crop_style": "random",
    "resolution": 1.0,
    "minimum_image_size": 0.25,
    "maximum_image_size": 1.0,
    "target_downsample_size": 1.0,
    "resolution_type": "area",
    "cache_dir_vae": "cache/vae/pixart/pseudo-camera-10k",
    "instance_data_dir": "/home/user/simpletuner/datasets/pseudo-camera-10k",
    "disabled": false,
    "skip_file_discovery": "",
    "caption_strategy": "filename",
    "metadata_backend": "discovery"
  },
  {
    "id": "text-embeds",
    "type": "local",
    "dataset_type": "text_embeds",
    "default": true,
    "cache_dir": "cache/text/pixart/pseudo-camera-10k",
    "disabled": false,
    "write_batch_size": 128
  }
]

Then, create a datasets directory:

mkdir -p datasets
pushd datasets
    huggingface-cli download --repo-type=dataset bghira/pseudo-camera-10k --local-dir=pseudo-camera-10k
popd

This will download about 10k photograph samples to your datasets/pseudo-camera-10k directory, which will be automatically created for you.

Login to WandB and Huggingface Hub

You'll want to login to WandB and HF Hub before beginning training, especially if you're using push_to_hub: true and --report_to=wandb.

If you're going to be pushing items to a Git LFS repository manually, you should also run git config --global credential.helper store

Run the following commands:

wandb login

and

huggingface-cli login

Follow the instructions to log in to both services.

Executing the training run

From the SimpleTuner directory, one simply has to run:

bash train.sh

This will begin the text embed and VAE output caching to disk.

For more information, see the dataloader and tutorial documents.

CLIP score tracking

If you wish to enable evaluations to score the model's performance, see this document for information on configuring and interpreting CLIP scores.

SageAttention

When using --attention_mechanism=sageattention, inference can be sped-up at validation time.

Note: This isn't compatible with every model configuration, but it's worth trying.