SoL-Refiner: one-step refinement turns low-res video into 4K with 8.91x latency speedup
Haozhe Liu · hf · 2026-09-30
SoL-Refiner is a one-step video refiner that converts low-resolution video model outputs into 4K with a single denoising step. Its three-stage recipe combines high-resolution continual training, RL post-training, and one-step distillation, with a new Refiner-Bench comparing refiners at 2K via a shared-input protocol. At 2K it beats all external refiners on VBench and UniPercept averages, and at 3840×2176 outperforms the three-step LTX-2.3 Refiner, achieving an 8.91x refinement latency speedup with the full acceleration stack.
Related event: SoL-Refiner Upscales Low-Res Video to 4K in One Denoising Step(2 posts)→
More from Multimodal
- Hand-editing 0.2% of weights plus 100 CPU-minutes turns an English TTS model into an 18MB Sanskrit one — kastnerkyle · 2026-11-16
- Zyphra open-sources textnorm tool, lifting TTS structured-data accuracy by up to 22 points — kastnerkyle · 2026-11-16
- Testing Qwen Image 2.1 and Minimax H3 on anime-to-photo conversion and film photo restoration — Ant_6431 · 2026-11-16
- Second take of a 'Cubee run' video generated with Minimax H3 — JahJedi · 2026-11-16
- Non-artist builds 14-chapter hand-painted storybook game with Fable 5.2 in 4 hours — jradoff · 2026-11-16
- Subject LoRAs on Minimax H3 Image learn poor likenesses while identical datasets excel on Qwen 2.1 — Ad_Organic · 2026-11-16