LivePortrait vs Merge

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.

Merge is an iOS app that turns a still photo and a reference motion video into an AI-generated motion video, with an optional style prompt. The site says generation takes under a minute. Listed creation types include AI dance videos, animated portraits, moving selfies and cinematic motion; output can reach 1080p. Users can save videos to their device or publish them to a community feed where people can browse and like them. Merge is listed for iPhone only and uses Apple Sign-In; Apple handles billing. Its free Starter plan includes 300 credits per month, Full HD videos and community feed access. Creator bills 1,000 credits per month and adds a priority generation queue, while Studio bills 3,000 credits per month and adds a top-priority queue. Selected photos are uploaded to temporary storage for generation and automatically deleted within about 48 hours. Merge lists English, Spanish, German, Dutch, Turkish and Russian.