LivePortrait distilled model that can run at 25fps in the browser
Summary
LivePortrait has been distilled into a model that can run at 25 frames per second directly in the browser, as shown in a Hugging Face Spaces demo by slperez.
View Cached Full Text
Cached at: 07/05/26, 10:39 PM
FLP Distillation Demo - a Hugging Face Space by slperez
Source: https://huggingface.co/spaces/slperez/flp-distillation-demo
Spaces
— https://huggingface.co/slperez 
slperez / flp-distillation-demo Running
Refreshing
Similar Articles
PersonaLive! Expressive Portrait Image Animation for Live Streaming
PersonaLive is a diffusion-based framework for real-time expressive portrait animation in live streaming, achieving significant speedups through hybrid implicit signals and autoregressive streaming generation.
LiveAnimate: Stable Long-Form Streaming Human Animation in Real-Time
LiveAnimate presents a 14B-parameter video diffusion transformer enabling real-time, long-form pose-driven human animation with stable streaming and constant memory usage via PR-Sink attention. Achieves 19.63 FPS inference on two H100 GPUs, maintaining quality over three-minute streams.
@maximelabonne: Perfection.
Liquid AI released LFM3 on Hugging Face, a ~2B shared-backbone model family spanning text, vision, audio, omni, and decision models, capable of real-time local video captioning in the browser via WebGPU with Transformers.js.
Real-time video captioning with LFM3-VL-2B running locally in-browser on WebGPU
LFM3-VL-2B 视觉语言模型可在浏览器中通过 WebGPU 本地实时进行视频字幕生成，LiquidAI 还发布了对应的 Hugging Face 模型集合与在线演示。
"Generate a photorealistic realtime render of a human face with webGL" (Qwen3.5-122B-A10B UD-Q3_K_XL)
A model (Qwen3.5-122B-A10B UD-Q3_K_XL) capable of generating photorealistic realtime renders of human faces using webGL.