Summary

SoL-Refiner enhances lower-resolution generated videos with a single high-resolution refinement step. High-resolution continual training, frame-based reinforcement learning, and distribution-matching distillation produce a one-step refiner for multiple base generators.

Key Features

Low-resolution video input.
Up to 4K refinement.
One target-resolution denoising step.
Cross-generator support.
Frame-based RL post-training.
One-step distillation.
Bidirectional inference.
Streaming inference.

About SoL-Refiner


Video developers can separate economical base generation from detail recovery instead of paying for repeated full-resolution denoising. Core capabilities include Low-resolution video input, Up to 4K refinement, One target-resolution denoising step, and Cross-generator support.


Public code or model weights are linked from the project, with setup instructions for running or adapting the system. Additional characteristics include Frame-based RL post-training, One-step distillation, Bidirectional inference, and Streaming inference.

Get more likes & reach the top of search results by adding this button on your site!

Embed button preview - Light theme
Embed button preview - Dark theme
TurboType Banner

Subscribe to the AI Search Newsletter

Get top updates in AI to your inbox every weekend. It's free!