Classifier-free guidance(CFG) is a fundamental tool in modern diffusion models for text-guided generation.
Although effective, CFG's reliance on high guidance scales presents notable drawbacks.
In response, we introduce simple solution to this seemingly inherent limitation: CFG++ .
This innovation addresses the off-manifold issue inherent in CFG, thereby enabling effective utilization
of small guidance scales (0 < $ \lambda $ < 1) .
|
CFG 😓 |
CFG++ 😁 |
T2I Generation |
Mode Collapse and Saturation |
Better Sample Quality & Adherence to text |
DDIM Inversion w/ CFG(++) |
Breakdown |
Improves and enables better image editing |
PF-ODE trajectory |
Unnatural, Curved |
Smooth, Straighter |
Experimental results confirm that our method significantly enhances performance in text-to-image generation,
DDIM inversion, editing, and solving inverse problems, suggesting a wide-ranging impact and potential applications
in various fields that utilize text guidance.