IG: Guiding a Diffusion Transformer with the Internal Dynamics of Itself
This repository contains the official PyTorch checkpoints for Internal Guidance.
Internal Guidance (IG) applies auxiliary supervision signals in the intermediate layers of the diffusion transformer network during training to assist in the training process. During inference, it utilizes the outputs of the intermediate and deeper layers to guide for better image generation results.
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support