YangLing0818 / RPG-DiffusionMaster

[ICML 2024] Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs (PRG)

https://arxiv.org/abs/2401.11708

Whether to release fine-tuning code

bank010 opened this issue 4 months ago · comments

MK commented 4 months ago

HUIZ-A commented 4 months ago

It's a training-free framework, isn't it?

Shuai Wang commented 3 months ago

Is the Complementary Regional Diffusion also training-free?