[CVPR 2026] Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient one-step diffusion framework for streaming VSR with locality-constrained sparse attention and a tiny conditional decoder.
Python · active 2025-10-15 → 2026-06-27 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 256 days from 2025-10-15 to 2026-06-27. Pushes: 16 total, peak 4 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 39 total, peak 4 in a day. Comments: 84 total, peak 14 in a day. Stars: 607 total, peak 26 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 |
|---|---|---|---|---|
| zhuang2002 | 36 | 16 | 0 | 16 |
| lihaoyun6 | 14 | 0 | 0 | 13 |
| naxci1 | 8 | 0 | 0 | 7 |
| gangxu822 | 8 | 0 | 0 | 5 |
| AdvancedHe | 5 | 0 | 0 | 1 |
| YZBPXX | 4 | 0 | 0 | 3 |
| kelisiyaer-ctrl | 4 | 0 | 0 | 3 |
| Teiboku | 4 | 0 | 0 | 1 |
| LujiaJin | 4 | 0 | 0 | 4 |
| zelenooki87 | 3 | 0 | 0 | 3 |
| qinLion | 3 | 0 | 0 | 2 |
| Manoa1911 | 2 | 0 | 0 | 1 |
| anthonyyuan | 2 | 0 | 0 | 2 |
| sinwel | 2 | 0 | 0 | 1 |
| SII-JerryZCY | 2 | 0 | 0 | 0 |
| The-unknown-Shadowman | 2 | 0 | 0 | 1 |
| danielwoz | 2 | 0 | 1 | 1 |
| wangshankun | 2 | 0 | 0 | 1 |
| hotdogarea | 2 | 0 | 0 | 1 |
| rainsoulsrx | 2 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue#106dex19902026-06-04 03:44How to compute peak memory in Table2?
- Issue comment#102icm1622026-05-09 05:03不支持处理短视频吗
- Issue comment#72Teiboku2026-04-09 16:56Question about evaluation scripts for quantitative metrics (PSNR / SSIM / LPIPS)
- Issue#96Chenlu-Y2026-03-18 10:27Periodic texture problem 周期性纹理问题
- Issue comment#92YZBPXX2026-03-13 03:46关于超分的倍率
- Issue comment#36YZBPXX2026-03-04 07:33no of output frames in the output is not same as input
- Issue#90Kai-Liu0012026-03-03 11:27请问数据集和training code的开源时间
- Issue#88zivkidd12026-02-11 01:44about Buffer_LQ4x_Proj and Causal_LQ4x_Proj
- Issue comment#80YZBPXX2026-02-06 05:38About the pixel l2 loss of stage 3
- Issue#86YZBPXX2026-01-30 09:49Will the training code be open-sourced?
- Issue comment#83BooHwang2026-01-30 08:03Color shifts in v1.1 weights
- Issue comment#82DavidBlenkinsopp2026-01-25 21:55installation issue
- Issue#80Teiboku2026-01-21 09:37About the pixel l2 loss of stage 3
- Issue#78SII-JerryZCY2026-01-21 07:27question about causal
- Issue#78SII-JerryZCY2026-01-21 07:14question about causal
- Issue comment#33LujiaJin2026-01-04 03:47About the upsacle
- Issue comment#40LujiaJin2026-01-04 03:40Distortion in face and text under 1.5x upscale
- Issue comment#61LujiaJin2026-01-04 03:20Wierd flicker effect in human face and hair
- Issue comment#64LujiaJin2026-01-04 03:17Time consumption of 12s video
- Issue#73yzhoulv2025-12-30 09:34Model fine-tuning with lora
- Issue#70Teiboku2025-12-27 08:30[Training] About the stage 1 training details
- Issue comment#38TmzComeLearn2025-12-26 11:384090d Linux video memory usage 情况
- Issue#69naxci12025-12-23 11:59ComfyUI-FlashVSR_Stable v.1.2
- Issue comment#59naxci12025-12-23 08:07ComfyUI-FlashVSR Stable version
- Issue comment#59naxci12025-12-22 17:57ComfyUI-FlashVSR Stable version
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 607 stars here means stars gained during the window, not the repo's star count.