search

Alpha-VLLM / Lumina-T2X

Lumina-T2X is a unified framework for Text to Any Modality Generation
MIT License
1.82k stars 74 forks source link

Question about lognorm #57

Closed jiashenggu closed 2 weeks ago

jiashenggu commented 2 weeks ago

Hi, great work! The paper mentions lognorm, but I couldn't find the implementation. Could you let me know if it's used in the code? If so, please tell me where I can find it. Thank you very much!

zhuole1025 commented 2 weeks ago

Thanks for your interest! The lognorm schedule is used in our ImageNet models. You can find the implementation here: https://github.com/Alpha-VLLM/Lumina-T2X/blob/04bb30bde5c2a1d2516251f6b9b92ad69bed2534/Next-DiT-ImageNet/transport/transport.py#L111

jiashenggu commented 2 weeks ago

Thanks for your interest! The lognorm schedule is used in our ImageNet models. You can find the implementation here: https://github.com/Alpha-VLLM/Lumina-T2X/blob/04bb30bde5c2a1d2516251f6b9b92ad69bed2534/Next-DiT-ImageNet/transport/transport.py#L111

Thank you for your response! I'm curious why you only use it in ImageNet.

zhuole1025 commented 2 weeks ago

That's because we tested the lognorm schedule only at the very beginning of our T2I project and found no significant improvements. However, it is worth paying more attention to the schedule for training large-scale flow and diffusion models.