Talking head video generation on Talkinghead1kh
19.37FIDFollow-your-emoji
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Follow-your-emojiRender Speed=0.5 FPS*, Resolution=512x512, Hardware=Nvidia A100 GPU2025.04 | 19.37 | 0.047 | 0.159 | 209.91 | |
| X-PortraitRender Speed=0.1 FPS*, Resolution=512x512, Hardware=Nvidia A100 GPU2025.04 | 19.86 | 0.045 | 0.164 | 183.05 | |
| IM-PortraitRender Speed=109 FPS, Resolution=512x512, Hardware=Nvidia A100 GPU2025.04 | 27.83 | 0.045 | 0.18 | 135.12 | |
| IM-Portrait w/o residualRender Speed=109 FPS, Resolution=512x512, Hardware=Nvidia A100 GPU2025.04 | 28.19 | 0.044 | 0.174 | 127.11 | |
| IM-Portrait w/o late-stageRender Speed=109 FPS, Resolution=512x512, Hardware=Nvidia A100 GPU2025.04 | 29.86 | 0.045 | 0.18 | 136.07 | |
| Face-V2VRender Speed=22 FPS, Resolution=256x256, Hardware=Nvidia A100 GPU2025.04 | 30.52 | 0.04 | 0.186 | 141.02 | |
| Portrait4d-v2Render Speed=10 FPS, Resolution=512x512, Hardware=Nvidia A100 GPU2025.04 | 37.38 | — | — | 227.32 | |
| EmoPortraitRender Speed=7 FPS, Resolution=512x512, Hardware=Nvidia A100 GPU2025.04 | 41.08 | 0.058 | 0.252 | 280.22 |