Luminous Landscape Forum
Equipment & Techniques => For Sale => Topic started by: plugsnpixels on October 19, 2022, 06:07:00 pm
-
Those of you working in video will be happy to hear that Topaz just released Video AI 3.0 and is offering a launch special of $140 off (http://'https://www.topazlabs.com/topaz-video-ai/ref/5/') using coupon GETVIDEOAI (good through 11/4).
Attached is a quick screenshot I made using a 1280×720 source upscaled to 4K:
Product release details:
Topaz built Video AI v3.0 from the ground up to include new functionality, such as video stabilization, improved enhancement capabilities, and a better user experience. Using this new code base allows them to provide some of your most requested features, such as:
▪Stacking AI models
▪Running tasks in parallel with filter support
▪Command-line interface
▪Important performance and stability improvements
Changes from 2.6.4:
GUI:
Completely new app from the ground up
Better stability
Models:
Stabilization
Apollo for super slow-mo
Completely Auto Proteus
TensorRT models for Deinterlace and Enhance models
Processing/Workflow:
Models can be chained
Command line support
Parallel execution support
Ability to keep previews
Usable offline once models are downloaded
Custom crop
Sharable presets
Output encoder can be modified by the user externally
Batch preview
Support for Intel Arc and Nvidia 4000 series
Outputs:
Support for various output formats
Color depth up to 16bit now supported
Colorspace and color inconsistency issues reduced significantly
On crashing, video files are playable
Handling non-square pixel videos
Metatag videoai added to videos with full filter details
-
Reminder, this sale (https://www.topazlabs.com/topaz-video-ai/ref/5/) ends tomorrow, 11/4.
-
The current sale for the latest version (http://'https://www.topazlabs.com/topaz-video-ai/ref/5') ends tomorrow, 1/31 (save $50).
v3.1.0
Released January 17th, 2023.
Changes from v3.0.12:
•Faster processing for all models
•New AI model for Motion Deblur (Themis)
•Faster preview playback
•Chronos, Chronos Fast, and Full Frame Stabilization uses TensorRT models on NVIDIA machines
•Noise and Grain settings are same as v2.6
•All filters and environment variables have been renamed to tvai from veai
•Export as generates intermediate files in the Export directory
•Stability improvement
•Misc. bug fixes and improvements