You're looking at a specific version of this model. Jump to the model overview.
zf-kbot /md-iu-video-enhancer-0126-2:e6b45f40
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| apikey |
string
|
|
API Key
|
| input_video |
string
|
输入视频文件(支持 mp4, mov, avi, mkv, webm)
|
|
| force_rate |
integer
|
24
Max: 60 |
强制帧率(0 表示保持原帧率)
|
| duration |
integer
|
30
|
最大处理时长
|
| enhance_mode |
None
|
0
|
增强模式选择,0=单flashvsr放大,1=1080P,2=2K,3=4K,4=4K+锐化
|
| flashvsr_pixels |
number
|
1
Min: 0.5 Max: 4 |
预处理总像素数上限(百万)
|
| flashvsr_ratio |
number
|
1
Min: 1 Max: 4 |
预处理缩放比例
|
| scale |
None
|
1
|
FlashVSR 超分倍率
|
| sparse_ratio |
number
|
2
Min: 1 Max: 4 |
稀疏比,2.0=稳定,1.5=更快
|
| kv_ratio |
number
|
3.5
Min: 1 Max: 8 |
KV 缓存比率
|
| local_range |
integer
|
7
Min: 7 Max: 11 |
局部范围,11=稳定,9=更锐利,7=效果最好
|
| color_fix |
boolean
|
True
|
颜色校正
|
| fix_method |
None
|
wavelet
|
颜色校正方法
|
| full_tiled |
boolean
|
True
|
启用分块处理(低显存)
|
| tiny_long |
boolean
|
False
|
启用 Tiny Long 模式(长视频优化)
|
| filename_prefix |
string
|
ImgUpscaler.ai
|
输出文件名前缀
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'items': {'format': 'uri', 'type': 'string'},
'title': 'Output',
'type': 'array'}