Immersity AI vs LivePortrait

Immersity AI is a service for converting images, with image-to-video and API access listed. Its maximum output resolution is 4K. The Free plan costs nothing and allows unlimited use, with conversions up to 720p; output is watermarked and for non-commercial use. The Image plan costs $4.99 a month and includes 500 conversion credits, output up to 4K, no watermarking, and commercial use. Image Pro costs $14.99 a month for 1,700 credits. Video costs $24.99 a month for 3,300 credits, Video Pro costs $49.99 a month for 7,500 credits, and Video Max costs $99.99 a month for 20,000 credits. Each paid plan supports output up to 4K, removes watermarks, and includes commercial use. The listed platform is API. Immersity AI is headquartered in Menlo Park, California, United States, and was founded in 2014.

LivePortrait creates portrait video from a single image, using motion from video, audio, text, or generation. It also supports editing portrait video using a source video and a driving video. Stitching and eye and lip retargeting controls provide ways to adjust animation. The project supplies inference code, pretrained models, and a Gradio interface for local use, as well as a demo hosted on Hugging Face Spaces. Its PyTorch implementation is released under the MIT License, and the project reports generation speed of 12.8 ms on an RTX 4090 GPU with PyTorch. Human-mode instructions cover Linux, Windows, and Apple Silicon macOS; Intel macOS is untested. Animal models can animate cats, dogs, and pandas using human-driven motion, but animal mode is tested only on Linux and Windows with an NVIDIA GPU and is unsupported on macOS. Local setup requires git, conda, FFmpeg, Python 3.10, and downloaded pretrained weights. Commercial users must replace the included InsightFace detection models. Maintainers warn of possible deepfake misuse and visual artifacts.