Parallel image generation in one pass: 0.74 Geneval from just 400 GPU-hours on four 96GB GPUs
_akhaliq · x · 2026-11-20
New paper "Jeveration / System One" generates images in a single parallel pass of 128 discrete tokens with bidirectional attention—no iterative denoising or autoregressive decoding—like Janus-Pro but with block decoding instead of token-by-token.
Training cost is remarkably low: starting from Qwen 3.5 4B with LoRA, only four 96GB GPUs and 400 total GPU-hours, reaching 0.74 on Geneval as a unified model. Caveat: standard VLM understanding scores aren't reported, so capability retention there is uncertain.
Related event: Jeveration: Frozen VLM Generates 512px Images in One Forward Pass, 78ms(5 posts)→
More from Multimodal
- CapCut launches ChatGPT video plugin: generate and edit timeline-based videos in chat — alifcoder · 2026-11-20
- Demi Guo previews real-time AI video model for directing films like a set — ying11231 · 2026-11-20
- Full automated GTA 6 content pipeline: Apify + ElevenLabs + Claude + Codex — eptwts · 2026-11-20
- 100% code-driven Blender squirrel film, made for $34.76 — no video gen models — dreamwieber · 2026-11-20
- ComfyUI Model Analytics 1.5.0 adds custom node usage analytics to find unused packages — Expert-Spread7618 · 2026-11-20
- HeyGen avatar quality jumps: 5-minute studio video now enough for a clone — toolstelegraph · 2026-11-20