Instructions to use oumoumad/ltx-2.3-dearchive-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use oumoumad/ltx-2.3-dearchive-lora with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Amazing work! Is there a guide?
Simply amazing work with your continued lora work Oumoumad! I had an idea for a restoration lora, and I was wondering if there was a guide? I have a 3090, so I hope that is capable of training.
Thank you for your time.
Not sure if you can train an IC LoRA with that, because it's ref and target videos at the same time, so it's double vram use, unlike classic loras.
Not sure if you can train an IC LoRA with that, because it's ref and target videos at the same time, so it's double vram use, unlike classic loras.
Oh, that's unfortunate. What GPU would be recommended, a 5090 or 6000 PRO?
You can fit into 5090 with small buckets, but if you target decent res with decent length you'll need more. With 6000 pro everything should pass, it's what I train on personally.