生成逼真的会说话的人像~[ACM MM 2025] FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis
active 2025-04-08 → 2026-03-20 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 347 days from 2025-04-08 to 2026-03-20. Pushes: 19 total, peak 4 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 26 total, peak 3 in a day. Comments: 56 total, peak 9 in a day. Stars: 769 total, peak 72 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| wangqiang9 | 21 | 11 | 0 | 7 |
| SoftologyPro | 6 | 0 | 0 | 6 |
| chaochao0 | 6 | 4 | 0 | 2 |
| frankjiang | 6 | 4 | 1 | 1 |
| wangxihao | 5 | 0 | 0 | 3 |
| min-star | 4 | 0 | 0 | 4 |
| aliok222 | 4 | 0 | 0 | 4 |
| FurkanGozukara | 4 | 0 | 0 | 4 |
| trashkollector | 4 | 0 | 0 | 2 |
| sebastianzehner | 4 | 0 | 0 | 4 |
| johndpope | 3 | 0 | 0 | 3 |
| doogyhatts | 3 | 0 | 0 | 2 |
| mingyangbj | 3 | 0 | 0 | 1 |
| clemarjonlaguardia | 2 | 0 | 0 | 1 |
| tianlinzx | 2 | 0 | 0 | 2 |
| LSI86 | 2 | 0 | 0 | 1 |
| SevenMpp | 2 | 0 | 0 | 1 |
| lith0613 | 2 | 0 | 0 | 0 |
| teyou | 2 | 0 | 0 | 1 |
| lwmming | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue#70wangxihao2025-09-15 00:36FantasyTalking loss
- Issue#69sungh662025-08-14 09:04后面会考虑使用sageattention的优化算法吗
- Issue#68wangjue-wzq2025-08-05 03:38Training time
- Issue#53xesdiny2025-07-16 02:34About 3.3.Identity Preservation Implementation
- Issue#28wangqiang92025-07-08 12:27what spec to run inference on 15 sec audio
- Issue#20wangqiang92025-07-08 12:26maximum duration of the generated result only 3s
- Issue comment#20wangqiang92025-07-08 12:26maximum duration of the generated result only 3s
- Issue#29wangqiang92025-07-08 12:23Occasional failure in generating first frame
- Issue comment#29wangqiang92025-07-08 12:23Occasional failure in generating first frame
- Issue comment#12wangqiang92025-07-08 12:22paper has been accepted by?
- Issue comment#56wangqiang92025-07-08 12:19"Is there any way for this model to generate a video longer than 30 seconds? I want to create long-form videos."
- Pull request#66frankjiang2025-07-07 13:52
- Issue#65trashkollector2025-06-21 21:30video/audio out of sync when running with Comfy
- Issue comment#64trashkollector2025-06-21 15:36How to improve inference speed？？？
- Issue#64SevenMpp2025-06-20 07:22How to improve inference speed？？？
- Issue#63trashkollector2025-06-19 16:36can you explain why this happens
- Issue comment#52SevenMpp2025-06-19 10:36Video quality degradation caused by multi-GPU parallel inference
- Issue comment#22min-star2025-06-17 03:29I am confused with the face encoder and motion module,it seems that couldn't found in the code
- Issue comment#45tianlinzx2025-06-17 01:53请问大概几个月后支持中文呢？
- Issue comment#15tianlinzx2025-06-17 01:48Any release plan of training codes?
- Issue comment#57trashkollector2025-06-14 05:52Lip Sync Off at Lower FPS
- Issue comment#40Zeyu-Zhu2025-06-05 08:18How to set motion intensity during inference?
- Issue#60ptmaster2025-05-31 15:16Need Chinese version, thank you!
- Issue comment#28teyou2025-05-31 04:03what spec to run inference on 15 sec audio
- Issue comment#34corvec2025-05-24 19:21Why 23 fps ?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 769 stars here means stars gained during the window, not the repo's star count.