-
So let's say there's a video with audio in multiple languages. And i would only be interested in one language. In my case Spanish. So i would like subgen to choose the Spanish audio track if available…
-
我运行以下脚本来extract vae latent，分辨率是768p（即WIDTH=1280，HEIGHT=768），NUM_FRAMES降到17了还是CUDA out of memory，这要怎么解决呢？
用的是8卡H800，80G显存。
```shell
#!/bin/bash
# This script is used for batch extract the vae…
-
When doing inference in a video, you need to use
`inference_state = predictor.init_state()`
to initialize the state, which will load all frames of the video, and if the video is large, it will take …
-
Hello! When I run the command: python3 train.py task=stickman_walk snapshot_load_dir=models/genrl_stickman_500k_2.pt num_train_frames=50_010 batch_size=32 batch_length=32 agent.imag_reward_fn=video_vi…
-
```python
#代码如下：
import cv2
import numpy as np
import queue
import threading
import time
from pydub import AudioSegment
import simpleaudio as sa
# 模拟音频帧生成
def generate_audio_frame…
-
## Environment
- **OS:** Windows
- **Scrcpy version:** 2.7
- **Installation method:** Windows release
- **Device model:**Oneplus Ace 3v
- **Android version:** 14
## Describe the bug
Wh…
-
I wanted to try `videomme` eval for a `llava-next-video` model, where the candidates are:
- `lmms-lab/LLaVA-NeXT-Video-7B`
- `lmms-lab/LLaVA-NeXT-Video-7B-DPO`
```
#!/bin/bash
export HF_TOKEN=X…
-
序：我因为这个项目受了不少折磨，也不清楚为什么这个Github项目的issue这么少，所以我能得到的帮助很少。我在成功地运行这个项目后，决定写下这个教程帮助后来人。
Preface: I was troubled a lot because of this project, and I don't know why there are so few issues in this …
-
I'm sure you are aware, just starting a thread for this specific issue. "Live Portrait Retargeting" as well as just using "Live Portrait Process" by itself, is a bit of a kluge when it comes to batchi…
-
Hello, I'm the student who is interested in Video Summarization task.
I've read some papers but I haven't found out is there any preprocessing steps needed before inputing frames of video into Google…