Open Feynman1999 opened 2 weeks ago
yes
Have you ever tried ablation experiments on the setting of t. Intuitively, an LR contains a lot more information than xt when T=1000. Is it because of the presence of Lora weight that T becomes less critical?
Can you share your understanding of time step settings, thanks!!
Hi, A larger T tends to generate more, while a smaller T tends to preserve fidelity.
T balances fidelity and perception. We aim for the better generation performance of OSEDiff, so we chose 999.
Have you ever tried ablation experiments on the setting of t. Intuitively, an LR contains a lot more information than xt when T=1000. Is it because of the presence of Lora weight that T becomes less critical?
Have you ever tried ablation experiments on the setting of t. Intuitively, an LR contains a lot more information than xt when T=1000. Is it because of the presence of Lora weight that T becomes less critical?
Your judgment is correct. Setting different T values at the input of UNet only affects the convergence speed, with little impact on the final model performance.
Is the time step directly fixed to T in the input of diffusion (the largest time step)