Live-portrait

Live-portrait

Live Portrait is an AI-driven portrait animation framework that transforms a single static photo into lifelike animated videos, producing realistic facial expressions, smooth head movement, and precise lip synchronization with fine-grained control.

Live-portrait is video generation software teams evaluate for video generation. Use this page to review pricing, integration signals, and the best alternatives before you commit.

Free API 70/100
#196 in Video Generation (196 tools)
Added 0 year ago
Data reviewed Jul 16, 2026

Profile facts come from the vendor source. AiMatch labels unknown pricing or API details instead of estimating them.

Review official source →

Quick Overview

Best for: Video Generation

What it does

Video Generation software for decision-makers comparing workflow fit and alternatives.

Best fit

Video Generation

Pricing snapshot

Free

Next step

Compare Live-portrait with similar tools before you shortlist it.

Compare this tool before you shortlist it

Review alternatives, pricing posture, and workflow fit side by side.

Live-portrait

Live Portrait is an AI-powered portrait animation framework that converts a single static portrait image into a realistic animated video. It produces controllable facial expressions, accurate lip movements, and smooth head motion using an implicit keypoint animation architecture and stitching/retargeting modules. The project emphasizes efficiency and practical usage — offering a free playground for experimentation and inference code and models on GitHub — making it suitable for researchers, developers, and creators who need production-oriented portrait animation and editing tools.

Live Portrait is an AI-driven portrait animation framework that transforms a single static photo into lifelike animated videos, producing realistic facial expressions, smooth head movement, and precise lip synchronization with fine-grained control.

Own this listing?

Claim this page for a one-time $29 to add pricing, features, screenshots, verified owner details, and a clearly labeled 30-day category position after the profile is live.

Claim this listing for $29

Key Features

Multi-Style Portrait Animation

Animates still images across various styles and sizes using stitching technology; supports realistic and stylized outputs (e.g., oil painting, sculpture, 3D rendering).

Portrait Video Editing with Stitching

Provides dynamic video-to-video face animation and editing capabilities using stitching modules to refine outputs.

Precise Eye Animation Control

Dynamically adjusts eye openness using scalar inputs for nuanced control over eye expressions.

Accurate Lip Movement Control

Fine-tunes lip positions with scalar-based inputs to achieve precise speech and expression animation.

Advanced Self-reenactment

Generates high-quality animations from a single source frame, designed to outperform existing methods in recreating dynamic video sequences.

Powerful Cross-reenactment

Transfers motion between different portraits robustly, handling large pose changes, subtle expressions, and multi-person inputs.

Implicit Keypoint Animation

Maps motion from a driving video onto the portrait using an implicit keypoint framework for controllable animation.

High Efficiency Video Synthesis

Optimized decoder rapidly generates frames to create smooth animations with high speed (reported 12.8ms per frame on an RTX 4090 using PyTorch).

Stitching and Retargeting Modules

Small MLP-based modules for refining outputs and providing fine-grained control and retargeting with minimal overhead.

Pricing

Free Tier Available

Free playground available at https://live-portrait.org/free-playground ("Start for Free" is shown on the site).

Use Cases

Self-reenactment

Animate a subject using motion derived from the same person’s driving video to recreate expressions and pose dynamics.

Cross-reenactment

Transfer motion from one person (driving video) to a different portrait to animate a target subject.

Portrait Animation from Still Images

Synthesize lifelike motion and expressions from a single static portrait photo.

Portrait Video Editing

Edit and retarget facial motion within existing portrait videos using stitching and retargeting modules.

Eye and Lip Retargeting Control

Precisely control eye openness and lip positions for nuanced expression or speech animation.

Style Transfer and Multi-style Animation

Render animations in different visual styles (realistic, oil painting, sculpture, 3D renderings).

Animal Animation (fine-tuning)

Can be fine-tuned to animate animals (cats, dogs, pandas) as noted in application scenarios.

Integrations

PyTorch

Framework used for model inference and performance reporting (implementation and timings reported using PyTorch).

GitHub (KwaiVGI/LivePortrait)

Inference code and pretrained models are hosted on GitHub for download, reproduction, and integration (https://github.com/KwaiVGI/LivePortrait).

NVIDIA GPUs (RTX 4090)

Performance benchmark reported on RTX 4090 hardware (12.8ms/frame) indicating GPU-accelerated inference compatibility.

Benefits

Generate lifelike animated videos from a single static photo, enabling realistic facial expressions and head motion.
Fine-grained control over eye, lip, and pose retargeting for precise expression editing.
High efficiency and speed for practical usage (reported 12.8ms/frame on RTX 4090) and availability of open-source inference code for integration and customization.

Limitations

No verified limitations are available.

Frequently Asked Questions

What is Live Portrait?
Live Portrait is a video-driven portrait animation framework that focuses on better generalization, controllability, and efficiency for practical usage. It's designed to synthesize lifelike videos from a single source image.
What are the main features of Live Portrait?
Main features include generating realistic videos from a single source image with motion derived from driving videos, audio, text, or generation; supports self-reenactment, cross-reenactment, eye and lip retargeting control, and multiple visual styles.
Who developed Live Portrait?
Live Portrait was developed by researchers from Kuaishou Technology, University of Science and Technology of China, and Fudan University.
What core technologies does Live Portrait use?
It uses an implicit-keypoint-based framework (built on vid2vid), mixed image-video training strategy, upgraded network architecture, motion transformation and optimization objectives, and stitching/retargeting modules with small MLPs.
What are the application scenarios for Live Portrait?
Application scenarios include self-reenactment, cross-reenactment, portrait animation from still images, portrait video editing, eye and lip retargeting control, animation across different styles, and fine-tuning for animal animation.
What is the performance of Live Portrait?
Reported generation speed is 12.8ms on an RTX 4090 GPU using PyTorch. The project used about 69 million high-quality frames for training to improve quality and generalization.
How can I get more information about the Live Portrait open-source project?
Inference code and models are available at https://github.com/KwaiVGI/LivePortrait; more detailed information and experimental results are on the project's GitHub page.
How can I start using Live Portrait for free?
To start using Live Portrait for free, visit the free playground at https://live-portrait.org/free-playground.

Getting Started

  1. 1 Step 1: Upload a clear portrait image — Live Portrait extracts facial features from the source photo.
  2. 2 Step 2: Select or upload a driving video that contains the facial movements to apply to the portrait.
  3. 3 Step 3: Click 'Animate', optionally adjust configuration parameters, then generate and wait for the animated video to be produced.

Support

email

Contact via the site email: [email protected] (listed in site footer).

docs

Inference code, models, and project details are available on the GitHub repository: https://github.com/KwaiVGI/LivePortrait.

web-playground

Try the tool directly via the Free Playground at https://live-portrait.org/free-playground.

API

Available: No
Documentation:

https://github.com/KwaiVGI/LivePortrait (inference code and models hosted on GitHub; no API described on the site)

Compare Live-portrait with similar tools

See how it stacks up against alternatives

Related Tools

View all 196 →
Contact for pricing
Agent2Creator

Agent2Creator

Agent2Creator is a Vidmoat-hosted social network where the users are autonomous AI agents that claim an identity, create videos using Vidmoat tools, and publish posts that include the build log of tool calls used to produce each video.

Video Generation
Enterprise-ready
Freemium
AI 3D pop-out videos for Reels, Shorts and ads

AI 3D pop-out videos for Reels, Shorts and ads

VideoPopy is an AI-powered 3D breakout video generator that creates short, platform-optimized pop-out videos (5s and 10s) for Reels, Shorts, Instagram, LinkedIn, Facebook and X to test product reveals and social creative without traditional production.

Video Generation
EndFrame

EndFrame

EndFrame is a macOS app that uses AI agents (Claude, ChatGPT, Grok) to build, render, and let you edit brand-aware launch videos, demos, tutorials, and social clips from prompts, repos, and dropped assets.

Video Generation
Free
ai-kissing-video-generator-free

ai-kissing-video-generator-free

AI Kissing Video Generator is a web-based tool that transforms static face photos into realistic, customizable kissing videos using deep learning algorithms. It targets users creating romantic memories, social media content, and professional pieces like wedding or marketing videos.

Video Generation
Free
Wondercraft

Wondercraft

Wondercraft is an AI video studio that combines best-in-class models for video, audio, voice, images, and sound into guided workflows and an editable studio to produce business-ready videos and audio content for teams and enterprises.

Video Generation
Freemium
no-code-ai-model-builder

no-code-ai-model-builder

Browser-based AI Avatar Generator that turns a single photo into a lip-synced talking video by uploading an image and audio or generating speech from text; outputs 720p/1080p and offers free and paid plans.

Video Generation
Freemium
Dovideo

Dovideo

Dovideo AI is an AI-driven video generator that creates short high-quality videos from text prompts, images, or existing videos, designed for storytellers, creators, and marketers.

Video Generation
Freemium
Aiphototalk

Aiphototalk

AI PhotoTalk transforms a single portrait photo into a lip-synced talking video in seconds using advanced AI—offering multi-language voice synthesis, 4K output, and a cloud-based workflow geared for creators, educators, and businesses.

Video Generation

Premium Alternatives

Paid
ai-image-and-video-generators

ai-image-and-video-generators

XYZ Generator is a web-based AI image and video generator that creates short videos and images from text prompts or images, targeting creators who need UGC, movies, and marketing assets.

Video Generation
Paid
Veo3-2

Veo3-2

Veo 3.2 is an AI-powered video generation model that converts reference images into expressive, high-quality videos with features like character and object consistency, native vertical (9:16) output, and 4K upscaling.

Video Generation
Paid
Shuffll

Shuffll

Shuffll is an enterprise-focused video infrastructure platform that automates generation of thousands of on‑brand videos from structured data via API, enforcing brand governance and embedding video capabilities directly into platforms and workflows.

Video Generation
Enterprise-ready
Paid
Veo4aivideo

Veo4aivideo

Veo 4 is an AI video generator for text-to-video and image-to-video creation that produces cinematic 8-second clips with synchronized native audio, cinematic motion, and multiple aspect ratio exports.

Video Generation
Paid
free-luma-ai-video-generator

free-luma-ai-video-generator

A Chinese entertainment and sports-technology company website (lumaaivideo.com) presenting multiple AI-driven sports and esports products and services such as AI matchmaking for esports陪玩, AI stadium crowd management, AI sports commentary simulation, and sports big-data analysis. The site provides contact details and tiered hourly pricing for services, but does not present a clearly labeled "free-luma-ai-video-generator" product page.

Video Generation
Paid
third-party-api-for-popular-ai-services

third-party-api-for-popular-ai-services

useapi.net offers an experimental unified REST API that connects customers' AI website accounts to many third-party AI services (images, video, music, speech, and face-swap), with a subscription model providing access and multi-account load balancing.

Video Generation
Enterprise-ready
Paid
shorts-faceless

shorts-faceless

ShortsFaceless is an AI-powered platform that automates creation of faceless short-form videos (YouTube Shorts, TikTok, Reels) by generating scripts, images, voiceovers, subtitles and exporting HD videos to help creators scale production quickly.

Video Generation
Paid
Gemini Omni

Gemini Omni

Gemini Omni is a multimodal AI video generator and editor that creates and iteratively edits videos from text, images, sketches, and uploaded clips—supporting conversational shot-by-shot edits, character consistency, and physics-aware scene simulation.

Video Generation

Explore Related Categories

Explore by Outcome