suimu
吐槽一下这个项目开源开的真的依托答辩
I copy the pab_mgr.py comm.py parallel_mgr.py files and open_sora_transformer_3d.py, and then use the command :torchrun --nproc_per_node 8 scripts/inference_pab.py configs/opensora-v1-2/inference/sample.py
my configuration parameter of pab is defalt
I use DSP too
and i wonder why your sample speed is so fast，192frames 480p noly 94s, is my H100's problem?
> [@suimuc](https://github.com/suimuc) Please use `--pretrained_lora_path xxx` in your terminal. These is no such option 
This is my script: CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7" python examples/wanvideo/train_wan_t2v_ours_audio.py --task train --train_architecture full --dataset_path data/example_dataset --output_path ./wan_training --dit_path "/home/shuchenweng/zhj/model-weight/Wan2.1-T2V-1.3B/diffusion_pytorch_model.safetensors" --max_epochs 10 --learning_rate 2e-5 --training_strategy deepspeed_stage_2 --use_gradient_checkpointing It can traning from pretrained succueefully:...
I meet the same question