VideoTuna
VideoTuna copied to clipboard
VideoVerses
Let's finetune video generation models!
Hello, I am training wan-2.1-i2v-14b on 8-card A800, but when saving the checkpoint, I get the following error: Training failed: [Errno 17] File exists: '/mmu_mllm_hdd_2/zuofei/VideoTuna/results/train/train_wanvideo_i2v_fullft_20250612153116/checkpoints/flow' [rank1]: Traceback (most recent call...
Hi Team, Can you share/guide me how to run inference on multiple GPU. I have 8, 24GB GPU. How to run the model in distributed manner. Or is there any...
hello, i was training wan2.1-14b-i2v-720p, but i found that i get two loss print after one step: Average Epoch time: 231.10 seconds Average Peak memory 68550.57MiB Epoch 0: 1%|▏ |...
Hi, I have been trying to fine-tune CogVideo5B-I2V both using LoRA weights and fully but independently of the number of epochs I train for, when I run the new checkpoints...
I've been trying to fix the lint error. The first run showed more than 3000 errors. There are way too many line too long (E501) and too complex functions (C901)...
Hello, do you have any full fine-tuning or LoRA fine-tuning codes for I2V models such as CogVideo5B-I2V or HunyuanVideo? Basically I am looking for text + image conditioning during fine-tuning...
