English | 简体中文(Simplified Chinese)

We provide a simple colab notebook to demonstrate how to build a diffusion model using the GenerativeRL library. You can access the notebook here.

We provide a simple colab notebook to demonstrate how to build a flow model using the GenerativeRL library. You can access the notebook here.

We provide a simple colab notebook to demonstrate how to generate samples from a trained generative model using the GenerativeRL library. You can access the notebook here.

We provide a simple colab notebook to demonstrate how to estimate the density of samples using a trained generative model using the GenerativeRL library. You can access the notebook here.

We provide several toy examples to demonstrate the features of the GenerativeRL library. You can access the examples here.

• Diffusion Model
• Energy condition Diffusion Model
• Independent Conditional Flow Matching Model
• Optimal Transport Conditional Flow Matching Model
• SF2M

• World Model

• Likelihood Evaluation

• DPM Solver
• SDE Solver

• Customized Neural Network Modules
• Dict-like Structure Data Generation

We provide an example to push a trained model to the Hugging Face website.

In this example, we push a trained LunarLanderContinuous model to the Hugging Face website, and automatically generate a model card using the template to showcase the model's detailed information.

We provide an example to pull a model from the Hugging Face website, and test the model's performance in the environment.