Omegance: A Single Parameter for Various Granularities in Diffusion-Based Synthesis
This provides a simple, adaptable solution for researchers and practitioners in AI/ML to fine-tune detail in diffusion models, but it is incremental as it builds on existing methods without a paradigm shift.
The paper tackles the problem of controlling granularity in diffusion-based synthesis by introducing a single parameter ω that adjusts detail levels during denoising, enabling precise control without retraining or significant overhead. It demonstrates impressive performance across image and video synthesis tasks, though no concrete numbers are provided.
In this work, we show that we only need a single parameter $ω$ to effectively control granularity in diffusion-based synthesis. This parameter is incorporated during the denoising steps of the diffusion model's reverse process. This simple approach does not require model retraining or architectural modifications and incurs negligible computational overhead, yet enables precise control over the level of details in the generated outputs. Moreover, spatial masks or denoising schedules with varying $ω$ values can be applied to achieve region-specific or timestep-specific granularity control. External control signals or reference images can guide the creation of precise $ω$ masks, allowing targeted granularity adjustments. Despite its simplicity, the method demonstrates impressive performance across various image and video synthesis tasks and is adaptable to advanced diffusion models. The code is available at https://github.com/itsmag11/Omegance.