根据基于 Diffusion 扩散模型的 AI 绘画方案发展脉络,对近期看的一些文章做个总结记录:
DDPM:Denoising Diffusion Probabilistic Models
DDIM:Denoising Diffusion Implicit Models
OpenAI, Classifier Guidance:Diffusion Models Beats GANs on Image Synthesis
LDM, Classifier-Free Guidance:High-Resolution Image Synthesis with Latent Diffusion Models
Scalable Diffusion Models with Transformers
SDXL:Improving Latent Diffusion Models for High-Resolution Image Synthesis
SDXL-Turbo:Adversarial Diffusion Distillation