Talking Head Generation on HDTF (test)
1.86FIDFW-C&W
Evaluation results
| Method | Links | |||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| FW-C&WModality=A2026.04 | 1.86 | — | — | — | — | — | — | — | — | — | — | — | — | — | 35.66 | 94 | 6.64 | 1.17 | — | — | — | — | — | — | — | |
| AA-C&WModality=A2026.04 | 1.96 | — | — | — | — | — | — | — | — | — | — | — | — | — | 33.59 | 93 | 6.5 | 1.38 | — | — | — | — | — | — | — | |
| AA-PGDModality=A2026.04 | 2.41 | — | — | — | — | — | — | — | — | — | — | — | — | — | 31.65 | 92 | 5.5 | 1.86 | — | — | — | — | — | — | — | |
| FW-PGDModality=A2026.04 | 2.56 | — | — | — | — | — | — | — | — | — | — | — | — | — | 31.21 | 91 | 5.89 | 1.79 | — | — | — | — | — | — | — | |
| MWModality=A2026.04 | 3.32 | — | — | — | — | — | — | — | — | — | — | — | — | — | 28.05 | 88 | 7.07 | 2.44 | — | — | — | — | — | — | — | |
| CAFModality=A2026.04 | 3.69 | — | — | — | — | — | — | — | — | — | — | — | — | — | 29.31 | 89 | 2.5 | 2.38 | — | — | — | — | — | — | — | |
| OmniAvatar2026.05 | 12.23 | 155.71 | 3.89 | 10.11 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| AVControl2026.03 | 12.31 | — | 4.5 | 10.31 | 0.18 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| AsymK-Talker2026.05 | 13.72 | 116.78 | 8.11 | 7.25 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Hallo32026.05 | 14.75 | 134.94 | 4.21 | 10.01 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| StableAvatar2026.05 | 15.89 | 146.79 | 7.01 | 8.49 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| TAVIDSource=Text2025.12 | 16.745 | 245.493 | — | — | — | — | — | 7.537 | 8.155 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ECHO2026.03 | 16.888 | 144.859 | — | — | — | — | — | 7.704 | 7.553 | — | — | — | — | 0.854 | — | — | — | — | — | — | — | — | — | — | — | |
| Hallo2Source=Audio2025.12 | 18.205 | 258.085 | — | — | — | — | — | 7.816 | 7.737 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ARIG2026.03 | 18.32 | — | — | — | — | — | — | — | — | — | — | — | — | 0.876 | — | — | — | — | — | — | — | — | — | — | — | |
| Hallo2Source=TTS2025.12 | 18.742 | 250.52 | — | — | — | — | — | 7.697 | 7.819 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| EchomimicSource=Audio2025.12 | 19.037 | 276.143 | — | — | — | — | — | 5.929 | 9.381 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| EchomimicSource=TTS2025.12 | 19.316 | 283.432 | — | — | — | — | — | 5.919 | 9.377 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| AvatarForcing2026.03 | 20.332 | 149.798 | — | — | — | — | — | 7.56 | 7.7 | — | — | — | — | 0.87 | — | — | — | — | — | — | — | — | — | — | — | |
| Hallo32026.03 | 20.359 | 160.838 | — | — | — | — | — | 7.252 | 8.106 | — | — | — | — | 0.865 | — | — | — | — | — | — | — | — | — | — | — | |
| Hallo2026.03 | 20.545 | 173.497 | — | — | — | — | — | 6.995 | 7.819 | — | — | — | — | 0.86 | — | — | — | — | — | — | — | — | — | — | — | |
| AniPortrait2026.05 | 21.33 | 238.48 | 2.97 | 11.91 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SadTalker2026.05 | 21.96 | 205.77 | 6.24 | 8.37 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Zhao et al.2026.04 | 23.27 | 315.236 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 79.47 | 5.88 | — | — | — | — | |
| SadTalker2026.03 | 23.34 | 203.86 | — | — | — | — | — | 7.171 | 8.046 | — | — | — | — | 0.821 | — | — | — | — | — | — | — | — | — | — | — | |
| SadTalkerSource=Audio2025.12 | 23.398 | 328.643 | — | — | — | — | — | 7.142 | 7.881 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| ActAvatarParams=5B, Resolution=720p, Time=16 min2025.12 | 23.471 | 301.064 | 7.663 | 7.545 | — | — | — | — | — | 4.12 | 2.714 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SadTalkerSource=TTS2025.12 | 23.51 | 328.539 | — | — | — | — | — | 7.227 | 7.756 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| StableAvatarParams=1.3B, Resolution=480p, Time=12 min2025.12 | 23.742 | 323.601 | 5.457 | 10.151 | — | — | — | — | — | 3.984 | 2.572 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Wan-S2VParams=14B, Resolution=720p, Time=68 min2025.12 | 23.85 | 299.491 | 7.462 | 7.745 | — | — | — | — | — | 4.108 | 2.684 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MultiTalk2026.03 | 24.01 | — | 8.54 | 6.69 | 1 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| OmniAvatarParams=14B, Resolution=480p, Time=36 min2025.12 | 24.398 | 374.594 | 7.986 | 7.696 | — | — | — | — | — | 4.088 | 2.664 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HunyuanVideo-AvatarParams=13B, Resolution=720p, Time=74 min2025.12 | 24.515 | 322.844 | 7.647 | 7.564 | — | — | — | — | — | 4.054 | 2.693 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MultiTalkParams=14B, Resolution=480p, Time=45 min2025.12 | 25.578 | 368.719 | 7.61 | 7.645 | — | — | — | — | — | 3.981 | 2.57 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FantasyTalkingParams=14B, Resolution=720p, Time=83 min2025.12 | 25.615 | 458.733 | 4.179 | 11.067 | — | — | — | — | — | 3.955 | 2.663 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| LatentSync2026.04 | 26.28 | 332.257 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 86.75 | 8.91 | — | — | — | — | |
| INFPImplementation=Reproduced version reported in [23]2026.03 | 27.155 | 187.977 | — | — | — | — | — | 7.325 | 7.81 | — | — | — | — | 0.84 | — | — | — | — | — | — | — | — | — | — | — | |
| MuseTalk2026.04 | 27.91 | 353.756 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 83.16 | 4.2 | — | — | — | — | |
| EAD-NetSTDA=✗, TFRM=✓2026.04 | 28.56 | 281.089 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 86.78 | 8.85 | — | — | — | — | |
| SonicMethod Type=Diffusion-based, Runtime=17.042024.11 | 29.104 | 301.173 | 4.197 | 9.371 | 1.745 | 95.95 | 99.7 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Sonic2026.03 | 29.53 | — | 8.35 | 6.43 | 1.22 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| FluentAvatarParadigm=autoregressive2025.09 | 29.72 | 260.65 | 5.57 | 10.39 | — | — | — | — | — | — | — | — | 0.24 | 0.95 | — | — | — | — | 18.69 | 73 | — | — | — | — | — | |
| EAD-Netmode=Ours (full)2026.04 | 29.91 | 312.347 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 86.39 | 9.04 | — | — | — | — | |
| HalloMethod Type=Diffusion-based, Runtime=74.652024.11 | 30.176 | 347.358 | 4.06 | 9.551 | 1.792 | 95.55 | 99.41 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Hallo3Params=5B, Resolution=480p, Time=32 min2025.12 | 30.424 | 318.451 | 6.994 | 8.647 | — | — | — | — | — | 3.883 | 2.488 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| EAD-NetSTDA=✓, TFRM=✗2026.04 | 30.8 | 319.795 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 86.36 | 9 | — | — | — | — | |
| IP_LAP2026.04 | 31.41 | 404.34 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 81.8 | 2.33 | — | — | — | — | |
| Wav2Lip2026.04 | 32.57 | 459.543 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 87.51 | 8.03 | — | — | — | — | |
| AniPortrait2026.03 | 32.83 | — | 3.09 | 10.94 | 1.32 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SonicParadigm=diffusion models2025.09 | 32.89 | 379.13 | 7.65 | 12.7 | — | — | — | — | — | — | — | — | 0.26 | 0.9 | — | — | — | — | 18.55 | 74 | — | — | — | — | — | |
| EchoMimicMethod Type=Diffusion-based, Runtime=5.452024.11 | 33.207 | 384.304 | 2.514 | 10.743 | 1.486 | 95.27 | 99.34 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Hallo32026.03 | 33.98 | — | 6.55 | 8.49 | 1.12 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| StableAvatarParadigm=diffusion models2025.09 | 35.39 | 700.82 | 5.34 | 12.56 | — | — | — | — | — | — | — | — | 0.28 | 0.85 | — | — | — | — | 18.41 | 72 | — | — | — | — | — | |
| AniPortraitMethod Type=Diffusion-based, Runtime=44.032024.11 | 36.965 | 471.452 | 1.095 | 12.461 | 3.161 | 95.08 | 99.21 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SadTalkerParadigm=GAN-based2025.09 | 37.2 | 316.78 | 5.72 | 11.83 | — | — | — | — | — | — | — | — | 0.26 | 0.82 | — | — | — | — | 18.85 | 74 | — | — | — | — | — | |
| EchoMimicParadigm=diffusion models2025.09 | 38.11 | 301.33 | 2.63 | 12.88 | — | — | — | — | — | — | — | — | 0.29 | 0.85 | — | — | — | — | 18.11 | 73 | — | — | — | — | — | |
| Hallo2Method Type=Diffusion-based, Runtime=45.752024.11 | 38.673 | 328.54 | 4.136 | 9.465 | 2.203 | 96.06 | 99.42 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| V-ExpressParadigm=diffusion models2025.09 | 40.13 | 779.19 | 5.29 | 12.79 | — | — | — | — | — | — | — | — | 0.27 | 0.88 | — | — | — | — | 18.29 | 72 | — | — | — | — | — | |
| AniPortraitParadigm=diffusion models2025.09 | 40.19 | 614.01 | 5.61 | 11.3 | — | — | — | — | — | — | — | — | 0.28 | 0.88 | — | — | — | — | 18.52 | 72 | — | — | — | — | — | |
| Hallo2Paradigm=diffusion models2025.09 | 42.77 | 340.83 | 6.37 | 11.91 | — | — | — | — | — | — | — | — | 0.25 | 0.89 | — | — | — | — | 19.04 | 75 | — | — | — | — | — | |
| EchoMimic v3Params=1.3B, Resolution=480p, Time=7 min2025.12 | 43.544 | 595.805 | 4.555 | 10.804 | — | — | — | — | — | 4.027 | 2.69 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| HalloParadigm=diffusion models2025.09 | 44.48 | 520.72 | 5.05 | 11.62 | — | — | — | — | — | — | — | — | 0.25 | 0.88 | — | — | — | — | 18.94 | 75 | — | — | — | — | — | |
| V-ExpressMethod Type=Diffusion-based, Runtime=39.042024.11 | 47.396 | 758.023 | 1.256 | 12.394 | 2.634 | 90.93 | 99.68 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| Hallo22026.04 | 53.47 | 413.951 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 66.68 | 5.82 | — | — | — | — | |
| SadTalkerMethod Type=GAN-based, Runtime=3.752024.11 | 61.672 | 397.114 | 1.755 | 10.695 | 2.482 | 92.87 | 99.61 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| SDS(-)Modality=V2026.04 | 79.8 | — | — | — | — | — | — | — | — | — | — | — | — | — | 20.04 | 66 | 6.35 | 2.99 | — | — | — | — | — | — | — | |
| PhotoGuardModality=V2026.04 | 107.19 | — | — | — | — | — | — | — | — | — | — | — | — | — | 17.16 | 64 | 6.61 | 3.17 | — | — | — | — | — | — | — | |
| Silencer-IModality=V2026.04 | 166.92 | — | — | — | — | — | — | — | — | — | — | — | — | — | 24.69 | 62 | 3.16 | 3.43 | — | — | — | — | — | — | — | |
| SDS(+)Modality=V2026.04 | 186.35 | — | — | — | — | — | — | — | — | — | — | — | — | — | 21.21 | 42 | 6.06 | 3.29 | — | — | — | — | — | — | — | |
| MISModality=V2026.04 | 203.74 | — | — | — | — | — | — | — | — | — | — | — | — | — | 23.03 | 57 | 2.84 | 3.83 | — | — | — | — | — | — | — | |
| SyncBreakerModality=AV2026.04 | 204.28 | — | — | — | — | — | — | — | — | — | — | — | — | — | 22.98 | 56 | 1.07 | 3.68 | — | — | — | — | — | — | — | |
| AdvDmModality=V2026.04 | 215.68 | — | — | — | — | — | — | — | — | — | — | — | — | — | 21.39 | 44 | 5.81 | 3.12 | — | — | — | — | — | — | — | |
| MistModality=V2026.04 | 256.21 | — | — | — | — | — | — | — | — | — | — | — | — | — | 21.04 | 61 | 4.78 | 3.36 | — | — | — | — | — | — | — | |
| A2P2026.06 | — | — | 0.519 | 0.341 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 17.64 | 0.03 | — | — | |
| AniPortrait2025.12 | — | 102.414 | — | — | — | — | — | 2.866 | 11.168 | — | — | 0.914 | 0.31 | — | — | — | — | — | — | — | — | — | — | — | — | |
| Audio2photoreal2026.06 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 9.676 | 21.332 | |
| DualTalk2026.06 | — | — | 0.346 | 0.467 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 26.06 | 0.18 | — | — | |
| DualTalk2026.06 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 8.806 | 2.074 | |
| EchoMimic2025.12 | — | 89.129 | — | — | — | — | — | 5.555 | 9.085 | — | — | 0.929 | 0.32 | — | — | — | — | — | — | — | — | — | — | — | — | |
| EchoMimicV22025.12 | — | 131.603 | — | — | — | — | — | 4.051 | 9.966 | — | — | 0.89 | 0.322 | — | — | — | — | — | — | — | — | — | — | — | — | |
| EmoTalk2026.06 | — | — | 0.412 | 0.429 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 23.52 | — | — | — | |
| EmoTalk2026.06 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 6.212 | 5.558 | |
| FacEDiT2025.12 | — | 31.662 | — | — | — | — | — | 7.96 | 6.95 | — | — | 0.93 | 0.289 | — | — | — | — | — | — | — | — | — | — | — | — | |
| Hallo2025.12 | — | 42.825 | — | — | — | — | — | 7.08 | 7.824 | — | — | 0.925 | 0.283 | — | — | — | — | — | — | — | — | — | — | — | — | |
| Hallo22025.12 | — | 43.13 | — | — | — | — | — | 7.038 | 7.815 | — | — | 0.927 | 0.281 | — | — | — | — | — | — | — | — | — | — | — | — | |
| Hallo32025.12 | — | 38.643 | — | — | — | — | — | 6.717 | 8.583 | — | — | 0.9 | 0.315 | — | — | — | — | — | — | — | — | — | — | — | — | |
| KeyFace2025.12 | — | 49.043 | — | — | — | — | — | 5.795 | 8.905 | — | — | 0.926 | 0.267 | — | — | — | — | — | — | — | — | — | — | — | — | |
| MindFlow2026.06 | — | — | 0.52 | 0.333 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 15.76 | 0.01 | — | — | |
| MindFlow2026.06 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 6.305 | 24.197 | |
| SadTalker2025.12 | — | 81.572 | — | — | — | — | — | 7.421 | 7.557 | — | — | 0.848 | 0.309 | — | — | — | — | — | — | — | — | — | — | — | — | |
| UniTalker2026.06 | — | — | 0.3 | 0.48 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 29.88 | — | — | — | |
| UniTalker2026.06 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 7.866 | 2.242 | |
| V-Express2025.12 | — | 65.158 | — | — | — | — | — | 7.842 | 7.47 | — | — | 0.906 | 0.341 | — | — | — | — | — | — | — | — | — | — | — | — |