Opus 5.5 + Midjourney: 'models have taste, you just point them right'
yuwen_lu_ · x · 2026-10-16
yuwenlu shares artworks generated by pairing Claude Opus 5.5 with Midjourney: classical portraits and still-life collages overlaid with object-detection-style boxes and confidence labels (face, peony, apple...), creating a 'computer-vision aesthetic' collage look. The author's take: models already have taste, you just need to point them in the right direction.
More from Multimodal
- FLUX 3 Upscaler hits Higgsfield: 50% faster and cheaper, native 2K/4K video — tisch_eins · 2026-10-16
- AI-generated "RiRi" images stun with photorealistic diamond-gown Rihanna looks — egeberkina · 2026-10-16
- SeedAudio 1.5 hits CapCut PC: one prompt generates dialogue, SFX and music — LearnWithBishal · 2026-10-16
- DLSS 5 Assetto Corsa demo stuns sim racers: 'better than reality' — CSProfKGD · 2026-10-16
- Video recast with fal agent: swap a character via one character sheet — adamho · 2026-10-16
- Dev open-sources Krea 2 pixel-art LoRA for 16x16 game icons with transparent backgrounds — Angaisb_ · 2026-10-16