search

YingqingHe / Awesome-LLMs-meet-Multimodal-Generation

🔥🔥🔥 A curated list of papers on LLMs-based multimodal generation (image, video, 3D and audio).
281 stars 16 forks source link

Consider to our work into your great repo #9

Closed YangLing0818 closed 3 months ago

YangLing0818 commented 3 months ago

Hi! This is a great repo to record the LLM-based generation/editing.

Would you like to add our ICML work into your repo and survey.

Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs, ICML 2024.

Arxiv: https://arxiv.org/abs/2401.11708

Code: https://github.com/YangLing0818/RPG-DiffusionMaster

YingqingHe commented 3 months ago

Thanks for your comment! We have added this great work!