Walter Hugo Lopez Pinaya

Removing alpha_max

2

Consider to remove alpha_max because it is not implemented in the original tipping code neither in the pronto implementation (only used in James implementation)

Enforce the zero terminal SNR to schedulers

11

According to "Common Diffusion Noise Schedules and Sample Steps are Flawed" (https://arxiv.org/pdf/2305.08891.pdf), the implementation of most schedulers do not use t = T in the sampling process. We should include...

Implement #293

Add tutorial on generative models trained using federated scenario

1

Create a tutorial that uses monai.fl tools to train a generative models. It can use any FL tools for it (reccomend start with NVFlare), but it should use MONAIAlgo or...

Similar to [RoentGen: Vision-Language Foundation Model for Chest X-ray Generation](https://arxiv.org/pdf/2211.12737.pdf), it would be good to be able to easily download the Stable diffusion model and then finetune it into a...

Implements #154

In order to make simpler the use of non-imaging data as conditioning, some new transformations could be added. For example, for text we have been using custom transformations to load...

Add a version of our [brain image generator](https://github.com/Project-MONAI/GenerativeModels/tree/main/model-zoo/models/brain_image_synthesis_latent_diffusion_model), that is conditioned on text sentences instead on float vectors (containing age, gender, and brain volumes). With this approach, it will be...

Add script to perform the conversion of the stable diffusion model to our classes (AutoencoderKL and DiffusionModelUNet)

Add tutorial performin Denoising based on "DDM: Self-Supervised Diffusion MRI Denoising with Generative Diffusion Models" https://openreview.net/forum?id=0vqjc50HfcC