Trajectory Consistency Distillation: Improved Latent Consistency Distillation by Semi-Linear Consistency Function with Trajectory Mapping
This addresses a specific bottleneck in accelerating text-to-image synthesis for AI image generation applications, representing an incremental improvement over existing consistency distillation methods.
The paper tackles the problem of Latent Consistency Models struggling to generate images with both clarity and detailed intricacy in text-to-image synthesis, and introduces Trajectory Consistency Distillation (TCD) which significantly enhances image quality at low NFEs and yields more detailed results compared to the teacher model at high NFEs.
Latent Consistency Model (LCM) extends the Consistency Model to the latent space and leverages the guided consistency distillation technique to achieve impressive performance in accelerating text-to-image synthesis. However, we observed that LCM struggles to generate images with both clarity and detailed intricacy. Consequently, we introduce Trajectory Consistency Distillation (TCD), which encompasses trajectory consistency function and strategic stochastic sampling. The trajectory consistency function diminishes the parameterisation and distillation errors by broadening the scope of the self-consistency boundary condition with trajectory mapping and endowing the TCD with the ability to accurately trace the entire trajectory of the Probability Flow ODE in semi-linear form with an Exponential Integrator. Additionally, strategic stochastic sampling provides explicit control of stochastic and circumvents the accumulated errors inherent in multi-step consistency sampling. Experiments demonstrate that TCD not only significantly enhances image quality at low NFEs but also yields more detailed results compared to the teacher model at high NFEs.