https://nalar.dev/tags/diffusion-models/ Recent content in Diffusion Models on Nalar Hugo en-us Sat, 05 Sep 2026 00:00:00 +0700 https://nalar.dev/understand-classifier-free-guidance-in-diffusion-models/ Sat, 05 Sep 2026 00:00:00 +0700 https://nalar.dev/understand-classifier-free-guidance-in-diffusion-models/ <p>A conditional diffusion model may understand a prompt and still produce samples that only weakly reflect it. During generation, developers therefore often want a way to push the denoising trajectory toward the condition without training a separate classifier for every prompt or label.</p> <p><strong>Classifier-free guidance</strong> (CFG) is a widely used way to do that. At each denoising step, the model is evaluated with the condition and without it. The difference between those predictions gives a direction associated with the condition, and a guidance scale controls how strongly sampling moves along that direction.</p>