Strong mode first downscales input media to 25% and then upscales to 4x.Īdded Full Disk Access prompt to resolve disk access errors on macOS. Standard mode first downscales input media to 50% and then upscales to 2x. Two different modes can be used to control the strength of this effect: This feature changes the way models affect input videos by downscaling inputs before upscaling. Improve missed focus in videos with the new "focus fix" mode for the Enhancement filter. Support for ACES and other color formats is still underway, and our team is actively seeking different use cases for EXR and DPX to further improve compatibility. This function requires a large amount of available disk space on the drive selected for exports. In a future update, auto-parameter estimation will be moved to the GPU to handle cases where Video AI is running on an incompatible CPU.ĮXR and DPX inputs will now be correctly downsampled to 16-bit TIFF for processing, and exported at 32-bit linear color. Reduced oversharpening and texture artifacts compared to Nyx v2.Īllows tweaking Sharpen slider value (Nyx Fast only).ĪVX2 requirement removed and replaced with a warning about possible errors. Improvements to processing speed - twice as fast as Nyx v2. Reduces ghosting of the previous frame at scene changes (same as Proteus v4).Īdds TensorRT models for faster inference on certain NVIDIA machines. Improves temporal consistency (reduces 'marching ant' artifacts). Improvements in detail, especially, for non-face inputs. Reduces ghosting of the previous frame at scene changes. Works on interlaced and interlaced progressive videos as well. Better handles noise and compression artifacts.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |