Two Resolutions, One Generation
JoLT generates large, densely detailed images by denoising low- and high-resolution latent streams together. The low-resolution stream preserves the overall composition, while the high-resolution stream builds local detail.
Unlike standard low-to-high pipelines, both resolutions evolve at the same time and continuously exchange information, reducing the usual trade-off between global coherence and local richness.
A Bidirectional Exchange
At every denoising step, JoLT turns the low-resolution estimate into a joint prior that guides the high-resolution tiled generation. The updated high-resolution canvas is then fed back into the low-resolution stream.
This bidirectional exchange synchronizes the two trajectories, helping fine details remain consistent with the global scene instead of being added only after the composition is already fixed.
Controlling Visual Complexity
JoLT gives artists direct control over image complexity. A master prompt defines the global scene, a detail prompt controls local appearance, and a single parameter α adjusts how strongly high-resolution detail influences the composition.
On 4096² images, JoLT produces substantially more measured visual complexity than strong high-resolution baselines while remaining competitive in text alignment, aesthetics, and overall quality.