New capabilities include the option to stack multiple AI models – for example, to upscale and stabilise footage simultaneously – and a new ‘Apollo’ AI retiming model for generating super-slo-mo footage. New in version 3.0: stack AI models, run tasks in parallel, and export at 16-bit colour depthĪs well as giving it a new name, Video AI 3.0 rewrites the software “from the ground up” to improve its handling of variable frame rate footage, frame repeats, and scene changes. Unlike Gigapixel, Video AI doesn’t have a dedicated mode for CG imagery, but it does upscale video footage to up to 8K, opening up the possibility of similar workflows for CG animation. Many visualisation artists use its still-image counterpart, Gigapixel AI, to upscale low-res 3D renders, making it possible to generate hi-res images more quickly than simply rendering at full resolution. While its main role is in video production, particularly to make poor-quality footage suitable for broadcast, or to upres old material for modern higher-resolution displays, it also has potential uses in CG work. Originally released in 2020, and previously known as Video Enhance AI, Video AI is an AI-trained tool capable of a range of video-processing tasks, including upresing, retiming and stabilising footage. (Full disclosure: the software was actually released last month, but we haven’t seen much coverage of it outside of general video production sites.)Īn AI-based tool for upresing video footage with potential applications to animation workflows The 3.0 release rewrites Video AI from the ground up, making it possible to apply multiple AI models simultaneously, and adding a new super-slo-mo AI model and support for 16-bit colour depth. Topaz Labs has released Video AI 3, the latest version of its AI-based software for upscaling, retiming and stabilising video, previously known as Video Enhance AI. Scroll down for news of the Video AI 3.1 update. We’ve also redesigned the app’s Preferences window layout to be easier to navigate and have made error messages more helpful by providing possible solutions to consider.Posted by Jim Thacker Topaz Labs ships Video AI 3.1 Making image sequence imports and exports more reliable.Fixing issues preventing a user from logging into the app.Resolving instances where the UI wouldn’t load consistently.Some of the more notable benefits involve: We’ve implemented many bug fixes and optimizations to make Topaz Video AI run more smoothly across a wider range of hardware. We also improved support of h.265 encoders for NVIDIA GTX GPUs. Mac users will now experience improved quality when exporting videos using h.264, h.265, and h.265 Main 10 encoders, and we added support for the AV1 encoder on Intel ARC GPUs. With Topaz Video AI v3.0.7, the AI models will receive the input media in the same color space that they were trained on, thereby increasing video quality. Our AI models perform best when the input video frames or image sequences are similar to the media used for training in terms of content, artifacts, color space (e.g. We’ve updated how some of our models work, which improves export video quality.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |