┃ ┣ 📂 Subject
┃ ┣ 📂 Action
┃ ┣ 📂 Environment
┃ ┣ 📂 Lighting
┃ ┣ 📂 Camera
┃ ┣ 📂 Style
┃ ┣ 📂 Mood
┃ ┗ 📂 Colors
┃
┣ 📂 Text Understanding
┃ ┣ 📂 CLIP
┃ ┣ 📂 T5
┃ ┣ 📂 Multimodal Encoders
┃ ┣ 📂 Semantic Embeddings
┃ ┗ 📂 Prompt Interpretation
┃
┣ 📂 Latent Space
┃ ┣ 📂 Compr...