Liquid: Language Models are Scalable and Unified Multi-modal Generators
active 2025-03-01 → 2026-03-28 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 393 days from 2025-03-01 to 2026-03-28. Pushes: 6 total, peak 3 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 13 total, peak 4 in a day. Comments: 14 total, peak 6 in a day. Stars: 262 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 |
|---|---|---|---|---|
| wjf5203 | 14 | 2 | 0 | 7 |
| iFighting | 3 | 3 | 0 | 0 |
| zhangzef | 2 | 0 | 0 | 1 |
| junzhin | 1 | 0 | 0 | 1 |
| zyandtom | 1 | 0 | 0 | 1 |
| bcaffee | 1 | 0 | 0 | 1 |
| akk-123 | 1 | 0 | 0 | 0 |
| yxchng | 1 | 0 | 0 | 0 |
| Yawningx | 1 | 0 | 0 | 0 |
| metildachee | 1 | 0 | 0 | 1 |
| ChunChenLin | 1 | 0 | 0 | 1 |
| EladWarshawsky | 1 | 0 | 0 | 1 |
| luckysheep861 | 1 | 0 | 0 | 0 |
| SummerRainQ | 1 | 0 | 0 | 0 |
| enjoyyi00 | 1 | 1 | 0 | 0 |
| lucky-liuzhihong | 1 | 0 | 0 | 0 |
| NielsRogge | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#20zyandtom2025-08-15 03:52Training detail
- Issue#22luckysheep8612025-07-01 07:28关于纯文本效果的一些问题
- Issue comment#12ChunChenLin2025-05-14 02:33Image Editing Capabilities
- Issue comment#21junzhin2025-05-10 05:59SFT detail
- Issue#20SummerRainQ2025-05-09 04:17Training detail
- Issue comment#18zhangzef2025-05-04 09:47How could I load the vqgan?
- Issue#18zhangzef2025-05-04 09:22How could I load the vqgan?
- Issue#16yxchng2025-04-19 13:43how many gpus are used/needed to train these models?
- Issue#15akk-1232025-04-18 08:56Does Liquid support generating both image and text tokens in a single generation sequence?
- Issue comment#12bcaffee2025-04-17 22:14Image Editing Capabilities
- Issue comment#12EladWarshawsky2025-04-17 05:26Image Editing Capabilities
- Issue comment#3wjf52032025-03-25 04:43Model Timeline
- Issue comment#3wjf52032025-03-25 04:42Model Timeline
- Issue#3wjf52032025-03-25 04:39Model Timeline
- Issue#10wjf52032025-03-25 04:38wrong number of image tokens
- Issue#8lucky-liuzhihong2025-03-07 05:32Failed to obtain a variable-resolution image.
- Issue comment#3metildachee2025-03-04 04:28Model Timeline
- Issue comment#6wjf52032025-03-04 02:47liquid_framework wording correction
- Issue#6wjf52032025-03-04 02:47liquid_framework wording correction
- Issue comment#5wjf52032025-03-04 02:41Release Liquid models on Hugging Face
- Issue#6Yawningx2025-03-04 02:38liquid_framework wording correction
- Issue comment#3wjf52032025-03-04 02:32Model Timeline
- Issue#3wjf52032025-03-04 02:32Model Timeline
- Issue comment#2wjf52032025-03-04 02:29How to maintain the original LLM language ability
- Issue comment#1wjf52032025-03-04 02:22mislabeling in the paper
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 262 stars here means stars gained during the window, not the repo's star count.