Multimodal generation
Conditioning, guidance and sampling schedules transfer across image models. Speech and image share almost nothing beyond the word “generation”.
Layer 34 entities0 started
Entities
Section titled “Entities”stable-diffusion
Not started. Becomes a package with its own syllabus once it begins.
flux
Not started. Becomes a package with its own syllabus once it begins.
tts-stt
Not started. Becomes a package with its own syllabus once it begins.
dalle
Not started. Becomes a package with its own syllabus once it begins.