Diffusion Models

NeMo 2.0 supports training diffusion models, including text-to-image and text-to-video models. NeMo 2.0 uses NeMo-Run to facilitate scaling across multiple GPUs. The following diffusion models are currently supported in NeMo 2.0:

• Flux
• Diffusion Training Framework

Default configurations are provided for each model and are outlined in the model-specific documentation linked above. Every configuration can be modified to train on new datasets or to test new model hyperparameters.