SkylerJulyApril
SkylerJulyApril
@daverim Hi, thank you very much for your help. Yes, I'm using x86 CPU, and I'm using the latest tf-nightly. I have a question, I installed tf-nightly with pip, do...
while I was doing the tflite quantization, I saw this "This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical...
I'm using tf-nightly right now (2.7 version), I tried with other stable versions, like 1.9 or 2.4, ended up with conversion errors. So I used the latest tf-nightly in the...
Hi @yahuuu , I also have this int tflite slower than float tflite, and mine is much slower actually. I checked my model with Netron, and except the input and...
What about supporting FiT for T2V?
I get this too, purple lips and eye color strange too, yellow-brown eyes. Anyone knows how to fix this?
I think there's something wrong with the tensorboardX, so I commented those lines because I don't need to use tensorboard to show me those summaries. And once you have commented...
evaluation is not working due to OOM issue. For training, I cannot use accelerate for 4 GPU model training, I can only use 1 GPU. Do you mind sharing your...
thank you very much for the sharing! I need to finetune my model and generate non square images, to do this, how shall i change the inference code?
@mihirp1998 Changing the dimensions can help generate non square images. But it does not work if I change the base model to sd2.1, resulting in nan in the loss.