Tony Lee

Finetune时GPU利用率波动很大

2

不做验证的时候纯训练，显存波动特别大，sft模式下从20多G到接近80G，波动范围特别大，这个有什么设置能解决吗，希望能持续保持在最大显存占用，尝试过关掉checkpoint_activations也还是会动态变化。

训练速度超级慢，请问要怎么设置才会提速呢？

8

感谢开源代码！目前在A100训练，关掉gradient_checkpoint，frames设置为33，其它设置保持官方代码不变，在6卡并行训练的时候单个iteration耗时约24秒，但是GPU利用率持续保持在100%的状态，请问哪里有什么别的设置能提高训练速度吗？

如何做长视频生成

1

现在的I2V只能生成49帧，如果想要生成更长视频要怎么实现呢

sampling is different between diffusers and sat ?

1

Hello, I am currently encountering an issue where the effect becomes noticeably blurry after using conversion code to transform a SAT training model into diffusers. I have pinpointed that the...

Can we do full training with 14b i2v model ?

3

Thank you very much for your framework, it’s very user-friendly. Regarding the training for wanx, is it possible to conduct full-parameter training on the 14B I2V model? I understand that...

Use DiffSynth-Studio to train i2v model based one wanx1.3 t2v model

3

Thank you for providing a very sleek and user-friendly diffusion framework. I’m currently trying to fine-tune the 14B i2v model, but there’s not enough VRAM. Is it possible to import...