view reply Have you tried mususi-tuner? It supports framepack's lora training. I've been trying it recently, but the results are not ideal.
view reply As far as I know, finetrainers doesn't support the training method proposed in the Framepack paper.So did you train according to the original HunyuanVideo-I2V method and only use Framepack during inference?
Llama 3.2 Collection This collection hosts the transformers and original repos of the Llama 3.2 and Llama Guard 3 • 15 items • Updated Dec 6, 2024 • 649