Lumina-Next-T2I

The Lumina-Next-T2I model uses Next-DiT with a 2B parameters model as well as using Gemma-2B as a text encoder. Compared with Lumina-T2I, it has faster inference speed, richer generation style, and more multilingual support, etc.

Our generative model has Next-DiT as the backbone, the text encoder is the Gemma 2B model, and the VAE uses a version of sdxl fine-tuned by stabilityai.

• Generation Model: Next-DiT
• Text Encoder: Gemma-2B
• VAE: stabilityai/sdxl-vae

paper

📰 News

• [2024-5-28] 🚀🚀🚀 We updated the Lumina-Next-T2I model to support 2K Resolution image generation.

• [2024-5-16] ❗❗❗ We have converted the .pth weights to .safetensors weights. Please pull the latest code to use demo.py for inference.

• [2024-5-12] 🚀🚀🚀 We release the next version of Lumina-T2I, called Lumina-Next-T2I for faster and lower memory usage image generation model.

🎮 Model Zoo

More checkpoints of our model will be released soon~

Installation

Before installation, ensure that you have a working nvcc

# The command should work and show the same version number as in our case. (12.1 in our case).
nvcc --version

On some outdated distros (e.g., CentOS 7), you may also want to check that a late enough version of gcc is available

# The command should work and show a version of at least 6.0.
# If not, consult distro-specific tutorials to obtain a newer version or build manually.
gcc --version

Downloading Lumina-T2X repo from GitHub:

git clone https://github.com/Alpha-VLLM/Lumina-T2X

1. Create a conda environment and install PyTorch

Note: You may want to adjust the CUDA version according to your driver version.

conda create -n Lumina_T2X -y
conda activate Lumina_T2X
conda install python=3.11 pytorch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 pytorch-cuda=12.1 -c pytorch -c nvidia -y

2. Install dependencies

pip install diffusers fairscale accelerate tensorboard transformers gradio torchdiffeq click

or you can use

cd lumina_next_t2i
pip install -r requirements.txt

3. Install flash-attn

pip install flash-attn --no-build-isolation

4. Install nvidia apex (optional)

[!Warning] While Apex can improve efficiency, it is not a must to make Lumina-T2X work.

Note that Lumina-T2X works smoothly with either:

• Apex not installed at all; OR
• Apex successfully installed with CUDA and C++ extensions.

However, it will fail when:

• A Python-only build of Apex is installed.

If the error No module named 'fused_layer_norm_cuda' appears, it typically means you are using a Python-only build of Apex. To resolve this, please run pip uninstall apex, and Lumina-T2X should then function correctly.

You can clone the repo and install following the official guidelines (note that we expect a full build, i.e., with CUDA and C++ extensions)

pip install ninja
git clone https://github.com/NVIDIA/apex
cd apex
# if pip >= 23.1 (ref: https://pip.pypa.io/en/stable/news/#v23-1) which supports multiple `--config-settings` with the same key...
pip install -v --disable-pip-version-check --no-cache-dir --no-build-isolation --config-settings "--build-option=--cpp_ext" --config-settings "--build-option=--cuda_ext" ./
# otherwise
pip install -v --disable-pip-version-check --no-cache-dir --no-build-isolation --global-option="--cpp_ext" --global-option="--cuda_ext" ./

Inference

To ensure that our generative model is ready to use right out of the box, we provide a user-friendly CLI program and a locally deployable Web Demo site.

CLI

1. Install Lumina-Next-T2I

pip install -e .

2. Prepare the pre-trained model

⭐⭐ (Recommended) you can use huggingface_cli to download our model:

huggingface-cli download --resume-download Alpha-VLLM/Lumina-Next-T2I --local-dir /path/to/ckpt

or using git for cloning the model you want to use:

git clone https://huggingface.co/Alpha-VLLM/Lumina-Next-T2I

1. Setting your personal inference configuration

Update your own personal inference settings to generate different styles of images, checking config/infer/config.yaml for detailed settings. Detailed config structure:

/path/to/ckpt should be a directory containing consolidated*.pth and model_args.pth

- settings:

  model:
    ckpt: "/path/to/ckpt"           # if ckpt is "", you should use `--ckpt` for passing model path when using `lumina` cli.
    ckpt_lm: ""                     # if ckpt is "", you should use `--ckpt_lm` for passing model path when using `lumina` cli.
    token: ""                       # if LLM is a huggingface gated repo, you should input your access token from huggingface and when token is "", you should `--token` for accessing the model.

  transport:
    path_type: "Linear"             # option: ["Linear", "GVP", "VP"]
    prediction: "velocity"          # option: ["velocity", "score", "noise"]
    loss_weight: "velocity"         # option: [None, "velocity", "likelihood"]
    sample_eps: 0.1
    train_eps: 0.2

  ode:
    atol: 1e-6                      # Absolute tolerance
    rtol: 1e-3                      # Relative tolerance
    reverse: false                  # option: true or false
    likelihood: false               # option: true or false

  in