For stable diffusion, not as much. Put the settings right and the training is done in 5 minutes. See the result, alter the settings and go again. Those settings are max possible batch size, previews off and saving checkpoint to off. Otherwise training takes 3 times longer or thrashes an SSD if used.
โ
For voice cloning, extensively. As soon as the loss changes or the loss updates stop it has to be killed. Worse is for newer ones like Style TTS, they have a constant VRAM usage up until a random point where it grows infinitely.
For stable diffusion, not as much. Put the settings right and the training is done in 5 minutes. See the result, alter the settings and go again. Those settings are max possible batch size, previews off and saving checkpoint to off. Otherwise training takes 3 times longer or thrashes an SSD if used.
โ
For voice cloning, extensively. As soon as the loss changes or the loss updates stop it has to be killed. Worse is for newer ones like Style TTS, they have a constant VRAM usage up until a random point where it grows infinitely.