One reference image keeps the person consistent across woodblock, pixel art, and infographics
techhalla · x · 2026-10-09
Designer @techhalla tested a new image generation model: feeding just one reference photo of herself, outputs stayed consistently her across woodblock prints, pixel art, boxed action figures, and full infographics — with realistic facial detail like wrinkles.
Standouts: text spelled correctly on the first try, actually readable infographics, and plain text-to-image that lands the style you asked for. Draft mode gives 16 takes per run to find a direction fast, and the author shared a space with 100+ prompts to steal.
More from Multimodal
- NAMVIS (NeurIPS 2026): next-scale autoregression beats diffusion for novel-view synthesis, 3x faster — RexDouglass · 2026-10-09
- fal Engineer on Video Speed: H3 Max Renders 15 Seconds of Video in 5 — OdinLovis · 2026-10-09
- Odyssey launches Odyssey-3, claims SOTA world model on Physics-IQ benchmark — Scobleizer · 2026-10-09
- One prompt, one full movie: dev shows multi-director agent pipeline for AI films — Exciting-Income-5840 · 2026-10-09
- Nano Banana 2.1 becomes Google's best image editing model across all 7 edit actions — ArtificialAnlys · 2026-10-09
- Nano Banana 2.1 Improves on All 9 Measured Image Capabilities, Biggest Gains in Layout and Anatomy — ArtificialAnlys · 2026-10-09