134. Design Text-to-Image Generation
Prompt to four images in seconds: latent diffusion, guidance, a distilled few-step student, recaptioned data, safety on both sides, watermarks and C2PA.
Pick a system. Work through the problem. Compare your approach.
Company tags are community-reported. Counts on cards show how many people reported that design.
Prompt to four images in seconds: latent diffusion, guidance, a distilled few-step student, recaptioned data, safety on both sides, watermarks and C2PA.
Faces of people who do not exist: a style-based GAN, truncation, latent-space edits, selfie inversion, provenance and memorisation audits.
Selfies in, professional headshots out: per-order LoRA on SDXL, an identity-encoder preview, face-match ranking, GPU pools, consent and deletion.
Images at 2K–4K without paying for every pixel: latent diffusion, an SR cascade with noise augmentation, tiled decoding, distilled drafts, cost per megapixel: one-hour boards for junior, senior and staff, with the theory.