Generative models · MLD-0177
Classifier-free guidance
A sampling technique combining conditional and unconditional predictions to strengthen adherence to a conditioning signal.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Make generated images follow a text prompt more closely.
Original caveat
Stronger guidance can reduce diversity or create artifacts.
Context and aliases
Level: Advanced. Stages: Architecture · Training · Inference.
Tags: DL · Generative AI · Vision.
Aliases: CFG.
Related concepts
Original references
- Denoising Diffusion Probabilistic Models ↗ · Consulted
- Deep Learning: online textbook ↗ · Consulted
- Flow Matching for Generative Modeling ↗ · Consulted
- Auto-Encoding Variational Bayes ↗ · Consulted
- Original reference URL ↗