The official code implementation of the paper "OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Data."
Python · active 2025-05-26 → 2026-01-27 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 247 days from 2025-05-26 to 2026-01-27. Pushes: 3 total, peak 1 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 18 total, peak 4 in a day. Comments: 22 total, peak 4 in a day. Stars: 241 total, peak 32 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 |
|---|---|---|---|---|
| lc03lc | 17 | 3 | 0 | 9 |
| ykj467422034 | 5 | 0 | 0 | 2 |
| nitinmukesh | 5 | 0 | 0 | 4 |
| WLiang-Chen | 2 | 0 | 0 | 1 |
| xiwj0916 | 1 | 0 | 0 | 0 |
| j2l | 1 | 0 | 0 | 1 |
| Harr7y | 1 | 0 | 0 | 0 |
| AdamShuo | 1 | 0 | 0 | 1 |
| cleverestx | 1 | 0 | 0 | 1 |
| ruanjiyang | 1 | 0 | 0 | 0 |
| StephanosPSteer | 1 | 0 | 0 | 1 |
| MaximClouser | 1 | 0 | 0 | 0 |
| ahmed20247 | 1 | 0 | 0 | 0 |
| EmmanuelMr18 | 1 | 0 | 0 | 1 |
| xiatiantuo | 1 | 0 | 0 | 0 |
| karthikg-09 | 1 | 0 | 0 | 1 |
| NielsRogge | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#21xiwj09162025-09-09 09:06How to obtain a benchmark dataset of 100 images?
- Issue#20echo-GU2025-07-24 05:08How to resolve OmniConsistency error message in huggingface app?
- Issue comment#18WLiang-Chen2025-07-10 11:13插个眼，放了训练代码大神说一声
- Issue comment#14ykj4674220342025-07-07 02:04About Nunchaku version
- Issue comment#14AdamShuo2025-07-06 14:48About Nunchaku version
- Issue comment#1j2l2025-07-05 10:53Anyway to use quantized transformer to reduce VRAM
- Issue#17ahmed202472025-06-17 11:36Model is not cached locally
- Issue#13WLiang-Chen2025-06-09 02:01The minimum number of styles the method can support
- Issue comment#2karthikg-092025-06-06 17:13Training code
- Issue comment#10lc03lc2025-06-04 05:30RuntimeError: Numpy is not available
- Issue comment#1nitinmukesh2025-06-03 10:59Anyway to use quantized transformer to reduce VRAM
- Issue#9ykj4674220342025-06-03 08:27Regarding the issue of subject_images？
- Issue comment#9ykj4674220342025-06-03 08:26Regarding the issue of subject_images？
- Issue comment#1cleverestx2025-06-03 06:12Anyway to use quantized transformer to reduce VRAM
- Issue comment#9lc03lc2025-06-03 03:33Regarding the issue of subject_images？
- Issue#9ykj4674220342025-06-03 02:02Regarding the issue of subject_images？
- Issue comment#1EmmanuelMr182025-06-02 22:36Anyway to use quantized transformer to reduce VRAM
- Issue comment#8nitinmukesh2025-06-02 17:01a quantified version?
- Issue#8xiatiantuo2025-06-02 16:38a quantified version?
- Issue comment#7lc03lc2025-06-02 14:48Combined with flux pulid
- Issue#7lc03lc2025-06-02 14:48Combined with flux pulid
- Issue comment#6lc03lc2025-05-30 10:54How to load unseen style LoRA?
- Issue#6lc03lc2025-05-30 10:54How to load unseen style LoRA?
- Issue#6lc03lc2025-05-30 10:24How to load unseen style LoRA?
- Issue comment#6lc03lc2025-05-30 10:23How to load unseen style LoRA?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 241 stars here means stars gained during the window, not the repo's star count.