[NeurIPS 2025 Oral]Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation
active 2025-11-06 → 2026-05-19 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 195 days from 2025-11-06 to 2026-05-19. Pushes: 16 total, peak 5 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 16 total, peak 2 in a day. Comments: 25 total, peak 6 in a day. Stars: 282 total, peak 47 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 |
|---|---|---|---|---|
| happylicio | 21 | 8 | 0 | 10 |
| JeyesHan | 10 | 6 | 0 | 3 |
| MingjieWe | 4 | 0 | 0 | 2 |
| drx-code | 2 | 0 | 0 | 1 |
| zwukong | 2 | 0 | 0 | 0 |
| gWeiXP | 2 | 0 | 0 | 2 |
| Treakun | 2 | 0 | 0 | 2 |
| enjoyyi00 | 2 | 2 | 0 | 0 |
| sen-mao | 1 | 0 | 0 | 0 |
| anr2me | 1 | 0 | 0 | 0 |
| Kurt232 | 1 | 0 | 0 | 1 |
| Sungwoong-Yune | 1 | 0 | 0 | 0 |
| johndpope | 1 | 0 | 0 | 1 |
| nuclearliu | 1 | 0 | 0 | 0 |
| xu-peng-7 | 1 | 0 | 0 | 1 |
| slacklife | 1 | 0 | 0 | 1 |
| Suheon-Jeong | 1 | 0 | 0 | 1 |
| tlennon-ie | 1 | 0 | 0 | 0 |
| imayeshakhatoon | 1 | 0 | 0 | 0 |
| chongbozhao3-coder | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#22happylicio2026-03-23 02:30Require a demo for second_v_clip generation.
- Issue#20happylicio2026-03-23 02:30Please Share VBench Hyper-Parameters
- Issue#33Sungwoong-Yune2026-02-02 02:43Reproduced VBench scores are significantly different from paper results (e.g., Multiple Objects)
- Issue comment#12johndpope2026-01-21 18:19How much GPU memory is required for 480p inference?
- Issue#32imayeshakhatoon2026-01-20 13:21Authentication rate limiting and token validation.
- Issue#30nuclearliu2026-01-04 11:59Question about scale repetition in training
- Issue#29sen-mao2025-12-27 12:30A question about the parameter `append_duration2caption`
- Issue comment#28happylicio2025-12-18 03:26关于提示词中的“Close-up on big objects, emphasize scale and detail”
- Issue comment#28gWeiXP2025-12-18 00:51关于提示词中的“Close-up on big objects, emphasize scale and detail”
- Issue comment#26Suheon-Jeong2025-12-18 00:39Text-to-image inference script
- Issue#18MingjieWe2025-12-09 07:01Training bug and question about batch size
- Issue comment#18JeyesHan2025-12-09 03:01Training bug and question about batch size
- Issue#23chongbozhao3-coder2025-12-04 03:34problem about bsq
- Issue comment#18MingjieWe2025-12-03 02:52Training bug and question about batch size
- Issue comment#20Kurt2322025-12-02 14:51Please Share VBench Hyper-Parameters
- Issue comment#16slacklife2025-11-28 06:00推理时报错：*** RuntimeError: input must be a CUDA tensor
- Issue comment#16happylicio2025-11-27 06:48推理时报错：*** RuntimeError: input must be a CUDA tensor
- Issue comment#17drx-code2025-11-27 06:03About Semantic Scale Repetition
- Issue comment#14MingjieWe2025-11-27 03:13Finetune ckpt inference fail
- Issue comment#14happylicio2025-11-27 02:58Finetune ckpt inference fail
- Issue#15happylicio2025-11-27 02:24Output quality mismatch: infer_video_720p.py result differs from Discord Web — Requesting official parameter settings
- Issue#17drx-code2025-11-26 12:54About Semantic Scale Repetition
- Issue comment#14happylicio2025-11-26 09:57Finetune ckpt inference fail
- Issue comment#14happylicio2025-11-26 07:26Finetune ckpt inference fail
- Issue comment#15xu-peng-72025-11-26 07:12Output quality mismatch: infer_video_720p.py result differs from Discord Web — Requesting official parameter settings
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 282 stars here means stars gained during the window, not the repo's star count.