Noise reduction effect with cinema level details

Video AI 4, trained on millions of video frames, can intelligently understand the difference between noise and detail

Identify people and faces, know exactly how to correct them

The vast desert and beautiful portraits are completely different, and the way you correct them should be the same. Video AI4 uses time aware facial recognition to automatically and instantly complete tasks.

Create a new frame using thin AI-r

Match cameras with different frame rates or achieve slow motion without changing camera settings. Apollo and Chronos models generate new frames, making them super smooth.

Stable in the later stage

Focus on the subject being photographed, rather than camera shake. Stabilize the image and restore details lost due to unnecessary camera movement, while reducing blur caused by motion and slow shutter speed. All in the later stage.

function

1. Directly compare UI, used to preview images and directly compare any two of the 24 AI models. Fine tune settings through side-by-side, sliding, and overlay views to achieve perfect video enhancement effects.

Video enhancement

1. Six Enhancement Models Trained for Quality Improvement of Different Types
2. Automatic mode for quick and easy processing, or manual control for fine-tuning output
3. Intelligent detection and repair of visual artifacts generated by video compression
4. Stack enhanced filter, capable of handling multi-step AI tasks with fewer clicks
5. Single frame rate or double frame rate de interleaving options
6. Specific processing pipelines for interlaced scanning and television content
7. 2x scaling mode enhances clarity and fidelity during denoising process
8. Iris MQ is used to enhance facial restoration
9. Custom mode for processing black and white videos
10. 3: 2. Custom mode for pulling down/reversing TV and movie materials

Steady Video

1. Including automatic cropping and full frame mode, with video external drawing
2. Additional options for rolling shutter correction and shake compensation

Frame interpolation

1. Using Apollo model for up to 16 times slow motion conversion
2. Interpolation up to 120FPS using Chronos

Motion deblurring

1. Reduce the impact of low shutter speed in fast-moving scenes

Wide range of export options

1. Create production grade output using ProRes and image sequence export options, integrating video AI into your existing workflow
2. Keep the original audio tracks in the material, or choose between multiple conversion options to create the best output for your work
3. Improved dynamic bitrate control: The "high" setting for H264 and H265 exports has been adjusted to a target VMAF score of approximately 95, which is now the default setting for newly installed video AI.
4. Optimize visual quality and file size using dynamic bitrate control on supported codecs
5. The lossless FFV1 codec is now available by default in the export options panel and can be used for 4:2:0, 4:2:2, and 4:4:4 chroma subsampling levels.

additional

1. 50% increase in GPU speed compatible with TensorRT
2. Support rotating videos by 90 degrees, 180 degrees, and 270 degrees - correcting videos lacking rotation metadata
3. AV1 encoder suitable for AMD 7000 series GPU and 700 series integrated graphics card