AI绘画系统有两个重要模块
Contrastive Language Image Pre-training (CLIP)
Diffusion Model
Dec/2021: High-Resolution Image Synthesis with Latent Diffusion Models
Ref: https://arxiv.org/pdf/2112.10752.pdf
2021/2022 state-of-art 结果,在当时主要针对pixel space
问题:如果运算资源不够强大,不能产生像样的结果,消费级GPU负担过大
New point:cross-attention layer