[CVPR 2024] Alpha-CLIP: A CLIP Model Focusing on Wherever You Want
active 2023-12-08 → 2026-01-29 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 784 days from 2023-12-08 to 2026-01-29. Pushes: 47 total, peak 10 in a day. Pull requests: 18 total, peak 6 in a day. Issues: 89 total, peak 6 in a day. Comments: 117 total, peak 9 in a day. Stars: 815 total, peak 34 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 |
|---|---|---|---|---|
| SunzeY | 121 | 28 | 8 | 67 |
| Aleafy | 30 | 19 | 8 | 3 |
| XuRui314 | 9 | 0 | 0 | 5 |
| xinli2008 | 7 | 0 | 0 | 5 |
| X1AOX1A | 6 | 0 | 0 | 3 |
| Originlightwkp | 5 | 0 | 0 | 2 |
| DavidGetter1 | 5 | 0 | 0 | 3 |
| vbayanag | 4 | 0 | 0 | 3 |
| LinMu7177 | 4 | 0 | 0 | 1 |
| Akshay1-6180 | 3 | 0 | 0 | 2 |
| donggoing | 3 | 0 | 0 | 1 |
| DesertsP | 3 | 0 | 0 | 1 |
| llf1234 | 3 | 0 | 0 | 1 |
| didiforgithub | 3 | 0 | 0 | 1 |
| YasuoFly | 3 | 0 | 0 | 2 |
| callsys | 3 | 0 | 0 | 1 |
| zhangh0920 | 3 | 0 | 0 | 1 |
| CharlesGong12 | 3 | 0 | 0 | 1 |
| LinQianhe02grey | 2 | 0 | 0 | 1 |
| lxysl | 2 | 0 | 0 | 2 |
Recent activity
Latest issues, pull requests and releases
- Issue#73fwbc2025-07-09 12:59Is AlphaClip only available in float32 type?
- Issue#71VincentTsai06012025-06-14 07:44Demo with llava
- Issue comment#70liweiyangv2025-04-17 01:14test set for region caption on VG dataset
- Issue comment#70SunzeY2025-04-16 11:53test set for region caption on VG dataset
- Issue comment#65e-meral-d2025-03-19 02:21alpha clip训练
- Issue comment#65SunzeY2025-03-18 12:53alpha clip训练
- Issue comment#65e-meral-d2025-03-18 08:46alpha clip训练
- Issue#69ascv02282025-02-12 03:48Does alphaclip have a model version suitable for sdxl?
- Issue comment#67jkff002025-01-18 09:43How to improve semantic differences between different objects
- Issue#68Lay-du2025-01-16 14:46Performance of image level visual language tasks for alpha-clip LLaVA-1.5
- Issue comment#65SunzeY2025-01-12 11:23alpha clip训练
- Issue comment#67SunzeY2025-01-11 15:28How to improve semantic differences between different objects
- Issue comment#67SunzeY2025-01-11 15:15How to improve semantic differences between different objects
- Issue comment#65dox0122025-01-08 03:12alpha clip训练
- Issue#67jkff002025-01-07 16:44How to improve semantic differences between different objects
- Issue comment#66SunzeY2025-01-07 16:35image patch embedding
- Issue comment#63SunzeY2025-01-07 16:32if i want The training input data is four channels, because my six-channel data is spliced from six single-channel 2D images. How should I modify the code? I do not have a mask annotation file. Can I use this code?
- Issue#66frederhoon2025-01-06 13:36image patch embedding
- Issue comment#65SunzeY2025-01-06 03:53alpha clip训练
- Issue#65dox0122025-01-05 16:16alpha clip训练
- Pull request#64YushunXiang2024-12-03 12:54
- Issue#63watertianyi2024-11-04 09:38if i want The training input data is four channels, because my six-channel data is spliced from six single-channel 2D images. How should I modify the code? I do not have a mask annotation file. Can I use this code?
- Issue comment#61SunzeY2024-08-20 03:29image default
- Issue#62Mxhjsz1232024-08-20 02:47大佬好
- Issue#61Mxhjsz1232024-08-20 02:46image default
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 815 stars here means stars gained during the window, not the repo's star count.