Official Implementation: Training-Free Efficient Video Generation via Dynamic Token Carving
active 2025-05-23 → 2025-12-29 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 221 days from 2025-05-23 to 2025-12-29. Pushes: 11 total, peak 4 in a day. Pull requests: 7 total, peak 2 in a day. Issues: 19 total, peak 2 in a day. Comments: 22 total, peak 3 in a day. Stars: 115 total, peak 28 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 |
|---|---|---|---|---|
| JulianJuaner | 31 | 11 | 5 | 11 |
| t0saki | 3 | 0 | 0 | 2 |
| EasonFasten | 3 | 0 | 0 | 1 |
| wangjiangshan0725 | 3 | 0 | 0 | 1 |
| sivenlu | 2 | 0 | 1 | 1 |
| armynew | 2 | 0 | 0 | 1 |
| splinter21 | 2 | 0 | 0 | 1 |
| Curat-D | 1 | 0 | 0 | 1 |
| zdyshine | 1 | 0 | 0 | 0 |
| fichas | 1 | 0 | 1 | 0 |
| xua222 | 1 | 0 | 0 | 1 |
| BienLuky | 1 | 0 | 0 | 0 |
| ClancyCC | 1 | 0 | 0 | 0 |
| snowflakewang | 1 | 0 | 0 | 0 |
| kabachuha | 1 | 0 | 0 | 0 |
| EladWarshawsky | 1 | 0 | 0 | 0 |
| Popping-Lock | 1 | 0 | 0 | 1 |
| MeiYi-dev | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue#11JulianJuaner2025-10-27 00:50Significant Content Discrepancy Between Jenga and Wan2.1 with the Same Seed
- Issue#12JulianJuaner2025-10-27 00:49Wan1.3B T2V Jenga runtime?
- Issue comment#22JulianJuaner2025-10-25 14:24Can the ProRes method make the results consistent?
- Issue#21snowflakewang2025-09-17 04:50Could the method be applied to other HunyuanVideo-based models?
- Issue#20BienLuky2025-09-02 10:24Wan2.1 inference time mismatch
- Issue comment#19xua2222025-08-14 09:58TeaCache for Wan2.1
- Pull request#18JulianJuaner2025-08-04 05:42
- Issue comment#18JulianJuaner2025-08-04 05:42fix: width and height bug
- Issue comment#18sivenlu2025-08-01 23:57fix: width and height bug
- Pull request#18sivenlu2025-08-01 23:54
- Issue#17jinyixin6212025-07-21 22:06Why is there no multi gpu inference for i2v models?
- Issue#16jxjx121382025-07-20 07:44AttributeError: 'WanModel' object has no attribute 'hilbert_order'
- Issue comment#15EasonFasten2025-07-07 09:40Inquiry about cuda memory
- Issue#15EasonFasten2025-07-07 09:40Inquiry about cuda memory
- Issue comment#15JulianJuaner2025-07-07 07:15Inquiry about cuda memory
- Issue#15EasonFasten2025-07-01 07:33Inquiry about cuda memory
- Issue comment#11JulianJuaner2025-06-30 03:33Significant Content Discrepancy Between Jenga and Wan2.1 with the Same Seed
- Issue#11JulianJuaner2025-06-30 03:33Significant Content Discrepancy Between Jenga and Wan2.1 with the Same Seed
- Issue comment#13JulianJuaner2025-06-28 09:23Wan1.3b Jenga Turbo
- Issue comment#14splinter212025-06-27 16:08虽然jenga_wan.py里写了很多不同采样步数下的attention参数策略，但是一点没传进去
- Issue#14splinter212025-06-27 16:08虽然jenga_wan.py里写了很多不同采样步数下的attention参数策略，但是一点没传进去
- Issue#13ClancyCC2025-06-26 15:59Wan1.3b Jenga Turbo
- Issue comment#11t0saki2025-06-26 07:34Significant Content Discrepancy Between Jenga and Wan2.1 with the Same Seed
- Issue comment#11JulianJuaner2025-06-25 07:51Significant Content Discrepancy Between Jenga and Wan2.1 with the Same Seed
- Issue comment#11t0saki2025-06-25 06:59Significant Content Discrepancy Between Jenga and Wan2.1 with the Same Seed
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 115 stars here means stars gained during the window, not the repo's star count.