[ICCV 2025] Official implementation of the paper “MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control”
active 2025-06-26 → 2026-05-08 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 317 days from 2025-06-26 to 2026-05-08. Pushes: 4 total, peak 4 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 13 total, peak 5 in a day. Comments: 17 total, peak 7 in a day. Stars: 106 total, peak 6 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 |
|---|---|---|---|---|
| flymin | 17 | 4 | 1 | 7 |
| jzliu02 | 2 | 0 | 0 | 1 |
| zzz5y | 1 | 0 | 0 | 1 |
| cghaocg | 1 | 0 | 0 | 0 |
| fenghe12 | 1 | 0 | 0 | 1 |
| cedricgsh | 1 | 0 | 0 | 0 |
| xiangli1117 | 1 | 0 | 0 | 1 |
| guoran-future-hu | 1 | 0 | 0 | 0 |
| JiachengZuo | 1 | 0 | 0 | 0 |
| zhoujiawei3 | 1 | 0 | 0 | 1 |
| Huster-YZY | 1 | 0 | 0 | 0 |
| dadadadabai | 1 | 0 | 0 | 1 |
| ArthurShelby-code | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#36zhoujiawei32026-01-07 08:07first frame as condition
- Issue comment#74jzliu022026-01-04 04:45About FVD calculation
- Issue#74jzliu022026-01-04 04:43About FVD calculation
- Issue comment#72dadadadabai2025-12-05 09:22Thank you for this amazing work! May I ask why the lane lines in my generated video become extremely messy after the 5-second mark? What could be causing this—could it be an issue with my settings?
- Issue comment#41xiangli11172025-12-04 11:35Environment
- Issue comment#41fenghe122025-12-04 11:27Environment
- Issue#69ArthurShelby-code2025-11-04 09:15Clarification on the “Trajectory” Condition in Figure 3 of MagicDrive V2
- Issue#68Huster-YZY2025-10-03 02:37Where is the MLLM generated Captions
- Issue#67cghaocg2025-09-25 08:59Whether the checkpoints provided by Hugging Face are finetuned with sp4 or sp8?
- Issue#62JiachengZuo2025-07-27 07:10config 1x224x400_stdit3_CogVAE_noTemp_xCE_wSST
- Issue comment#61dimkal892025-07-24 09:02Stage 3 checkpoint FVD performance
- Issue comment#61dimkal892025-07-24 08:16Stage 3 checkpoint FVD performance
- Issue#57flymin2025-07-24 02:30Why adopt an architecture different from MagicDrive?
- Issue comment#59flymin2025-07-24 02:25公式2有问题吗？里面的z是什么？
- Issue comment#60flymin2025-07-24 02:23Experienced training crash after switching from 8 GPUs to 16 GPUs
- Issue#60guoran-future-hu2025-07-10 14:18Experienced training crash after switching from 8 GPUs to 16 GPUs
- Issue#38cedricgsh2025-07-04 06:29How long does it take to train stage 2
- Issue comment#26zzz5y2025-06-30 07:56Can i inference 1 frames by 150 times to get a full length render results?
- Issue#30flymin2025-06-26 09:05Training Logs
- Issue comment#56flymin2025-06-26 09:05Train
- Issue#24flymin2025-06-26 09:02Can i inference based on my custom data?
- Issue#32flymin2025-06-26 08:54lib/python3.9/site-packages/nuscenes/map_expansion/map_api.py:1838: ShapelyDeprecationWarning
- Issue comment#42flymin2025-06-26 08:53pretrained weight for stage 1 & 2？
- Issue#36flymin2025-06-26 08:51first frame as condition
- Issue comment#37flymin2025-06-26 08:50run out of memory
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 106 stars here means stars gained during the window, not the repo's star count.