TransfusionModel

Combine LanguageModels with DiffusionModels

So that the LLM can drive image generation

https://openai.com/index/introducing-4o-image-generation/

https://arxiv.org/abs/2405.09818

https://arxiv.org/abs/2408.11039

Not to be confused with LanguageDiffusionModels which generate text by a diffusion-like process