sahil
sahil
Thanks a lot for it. Can you please let me know how can I train this on imagenet or caltech101 dataset as a contionalGAN? That would really help in data...
Also can you provide me the exact code for generating class base images in cifar 10. When I'm replacing it by sample.py it's showing me errors.
@lucasjinreal Actually you cant, its only saving the Lora weights, whereas u need the config.json file and non_lora_trainables.bin, which are saved after the training is done. This is the problem...
@daiyixiang666 theoretically i don't understand why it should perform badly, depends on how you are doing the conditioning.
@iFighting While it's true that autoregressive models can generate high-quality images without relying on text-based or mask-based conditioning, it's important to acknowledge that diffusion-based models like DiT have also demonstrated...
For control generation (reference): https://arxiv.org/pdf/2406.09750
@federico1-creator This is not solved even after commenting that line. Can u look into it
@federico1-creator Thanks for this will check it.