β β£ π Subject
β β£ π Action
β β£ π Environment
β β£ π Lighting
β β£ π Camera
β β£ π Style
β β£ π Mood
β β π Colors
β
β£ π Text Understanding
β β£ π CLIP
β β£ π T5
β β£ π Multimodal Encoders
β β£ π Semantic Embeddings
β β π Prompt Interpretation
β
β£ π Latent Space
β β£ π Compr...