DiffArtist: Towards Aesthetic-Aligned Diffusion Model Control for Training-free Text-Driven Stylization
AI & ML interests
None defined yet.
DiffArtist: Towards Aesthetic-Aligned Diffusion Model Control for Training-free Text-Driven Stylization
VideoMind: A Chain-of-LoRA Agent for Long Video Reasoning
PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLM
[NeurIPS 2024] Towards Open-Ended Event-Level Video-Language Understanding