Real-time generation demo shows hybrid image model generating whole-image codes first
ostrisai · x · 2026-09-20
Ostris shares a real-time generation clip of his AR/diffusion hybrid image model (Qwen3-VL-4B + frozen BFL Klein 4B): codes for the whole image are generated first, then decoded — with no inference optimizations applied.
More from Multimodal
- Seedance Draft on Plot Party: cheaper AI video prototyping before final renders — umesh_ai · 2026-11-04
- Sampler face-off at 8-16 steps on flow models: grids and LPIPS data — YakovSava · 2026-11-04
- INT8 isn't the problem: I benchmarked samplers on INT8 flow models — YakovSava · 2026-11-04
- Seedance 2.5 AI video of a wild Malfoy is turning heads — nikola_mr64990 · 2026-11-04
- Free course covers the 4 hard problems of production generative media agents — Al_Grigor · 2026-11-04
- PixelBench: testing multimodal models pixel-by-pixel instead of with QA — bdsqlsz · 2026-11-04