MagicPose

Realistic human pose and facial expression transfer from video.

Open SourceSelf HostedOffline CapableGPU Required (12GB+ VRAM)
0.0 (0)

About

MagicPose is an identity-aware diffusion model for retargeting human poses and facial expressions from a driving video onto a still reference image. It preserves the subject's appearance, clothing, and identity while producing video with new motion and expressions, and is compared in the paper against MagicAnimate, Disco, and TPS. Code, pretrained models, and a Hugging Face demo are released by the USC and ByteDance authors.

Reviews (0)

Leave a Review

No reviews yet. Be the first to review!

Details

Price
Free
Platform
Local/Desktop
Difficulty
Advanced (4/5)
Minimum VRAM
12 GB
Added
Apr 3, 2026

Related Tools

Real-time high-quality lip-sync model for audio-driven talking face generation.

Open SourceSelf HostedOfflineGPU 6GB+
Intermediate
0.0 (0)
Featured

Audio-driven talking head animation from a single image.

Open SourceSelf HostedOfflineGPU 6GB+
Easy
0.0 (0)

Audio-driven portrait animation with lifelike expressions and head movements.

Open SourceSelf HostedOfflineGPU 8GB+
Intermediate
0.0 (0)

Hierarchical audio-driven visual synthesis for portrait animation.

Open SourceSelf HostedOfflineGPU 8GB+
Intermediate
0.0 (0)
Featured

Accurately lip-sync videos to any audio using a pre-trained model.

Open SourceSelf HostedOfflineGPU 4GB+
Easy
0.0 (0)
Featured

Efficient portrait animation framework for stitching and retargeting.

Open SourceSelf HostedOfflineGPU 6GB+
Easy
0.0 (0)
Browse all AI Animation & Motion tools