List your company

Talking Head Video Generation on HDTF

14.76FIDIM-Portrait w/o residual
11.2555634.9105358.565582.22047Nov 24, 2024Dec 19, 2024Jan 14, 2025Feb 9, 2025Mar 6, 2025Apr 1, 2025Apr 27, 2025

Evaluation results

MethodLinks
IM-Portrait w/o residualRender Speed=109 FPS, Resolution=512x512, Hardware=Nvidia A100 GPU2025.0414.760.030.11665.75
X-PortraitRender Speed=0.1 FPS*, Resolution=512x512, Hardware=Nvidia A100 GPU, Mechanism=Diffusion-based2025.0415.660.0340.119132.9
IM-PortraitRender Speed=109 FPS, Resolution=512x512, Hardware=Nvidia A100 GPU2025.0415.930.0310.11869.04
Follow-your-emojiRender Speed=0.5 FPS*, Resolution=512x512, Hardware=Nvidia A100 GPU, Mechanism=Diffusion-based2025.0416.090.0350.115117.54
IM-Portrait w/o late-stageRender Speed=109 FPS, Resolution=512x512, Hardware=Nvidia A100 GPU2025.0416.70.0310.12370.69
Face-V2VRender Speed=22 FPS, Resolution=256x256, Hardware=Nvidia A100 GPU2025.0420.570.0290.13278.11
EmoPortraitRender Speed=7 FPS, Resolution=512x512, Hardware=Nvidia A100 GPU2025.0424.770.0390.189140.51
Portrait4d-v2Render Speed=10 FPS, Resolution=512x512, Hardware=Nvidia A100 GPU2025.0425.74——139.11
LetsTalk-L# Params=0.7B, Latency (ms)=402024.1131.761———
Hallo# Params=2.4B, Latency (ms)=1152024.1144.343———
LetsTalk-B# Params=0.3B, Latency (ms)=272024.1146.24———
EchoMimic# Params=2.2B, Latency (ms)=542024.1155.791———
AniPortrait# Params=2.6B, Latency (ms)=742024.1178.284———
SadTalker# Params=138M, Latency (ms)=232024.11102.371———