Text to Image

GAN, VAE, Diffusion, CLIP, DALL·E, Stable AI, Midjourney, Pika, …

Products

Reference

• DALL·E, VAE, dVAE, VQVAE
  • CLIP
    • https://openai.com/research/clip
  • DALL·E
    • https://openai.com/research/dall-e
    • https://zhuanlan.zhihu.com/p/394467135
• DALL·E 2, Diffusion, GLIDE
  • Diffusion
    • https://arxiv.org/abs/2006.11239
    • https://zhuanlan.zhihu.com/p/599887666
  • GLIDE
    • https://arxiv.org/abs/2112.10741
  • DALL·E 2
    • https://arxiv.org/abs/2204.06125
    • https://openai.com/dall-e-2
    • https://www.assemblyai.com/blog/how-dall-e-2-actually-works/
• DALL·E 3
  • DALL·E 3
    • https://cdn.openai.com/papers/dall-e-3.pdf
• Stable Diffusion
  • Latent & Conditional Diffusion
    • https://arxiv.org/pdf/2112.10752.pdf
    • https://github.com/CompVis/latent-diffusion
    • https://zhuanlan.zhihu.com/p/600251419
• Pika
  • On Distillation of Guided Diffusion Models
    • https://arxiv.org/pdf/2210.03142.pdf
    • Used in Google ImageGen
  • https://cs.stanford.edu/~chenlin/
• Imagen
  • https://www.assemblyai.com/blog/how-imagen-actually-works/