Official repository of T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
active 2025-05-01 → 2026-04-07 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 342 days from 2025-05-01 to 2026-04-07. Pushes: 16 total, peak 4 in a day. Pull requests: 1 total, peak 1 in a day. Issues: 23 total, peak 3 in a day. Comments: 37 total, peak 5 in a day. Stars: 337 total, peak 38 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 |
|---|---|---|---|---|
| CaraJ7 | 37 | 12 | 1 | 19 |
| yujinhanml | 4 | 0 | 0 | 4 |
| micky-li-hd | 4 | 0 | 0 | 2 |
| wtc9806 | 3 | 0 | 0 | 2 |
| Lxiangyue | 3 | 0 | 0 | 1 |
| SummerWXK | 2 | 0 | 0 | 0 |
| fake-warrior8 | 2 | 0 | 0 | 1 |
| NielsRogge | 2 | 0 | 0 | 1 |
| Upper9527 | 2 | 0 | 0 | 1 |
| ezyyeah | 2 | 0 | 0 | 2 |
| EmmaThompson123 | 1 | 0 | 0 | 0 |
| ZrrSkywalker | 1 | 1 | 0 | 0 |
| jaclyngu | 1 | 0 | 0 | 0 |
| jjhaggar | 1 | 0 | 0 | 0 |
| ZiyuGuo99 | 1 | 1 | 0 | 0 |
| hbbOooO | 1 | 0 | 0 | 1 |
| Astroburner | 1 | 0 | 0 | 0 |
| johnsonkao0213 | 1 | 0 | 0 | 1 |
| HalvesChen | 1 | 0 | 0 | 0 |
| eslambakr | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#12yujinhanml2025-09-10 10:08Evaluation Code of T2I-CompBench
- Issue comment#12CaraJ72025-09-10 09:52Evaluation Code of T2I-CompBench
- Issue comment#12yujinhanml2025-09-10 09:11Evaluation Code of T2I-CompBench
- Issue comment#12CaraJ72025-09-10 07:07Evaluation Code of T2I-CompBench
- Issue comment#12yujinhanml2025-09-10 05:59Evaluation Code of T2I-CompBench
- Issue comment#12CaraJ72025-08-27 07:59Evaluation Code of T2I-CompBench
- Issue comment#12yujinhanml2025-08-27 06:57Evaluation Code of T2I-CompBench
- Issue comment#14CaraJ72025-08-21 02:48Reproducing issues
- Issue comment#14johnsonkao02132025-08-20 21:24Reproducing issues
- Issue comment#16Lxiangyue2025-08-12 05:26TypeError: LlavaQwenForCausalLM.forward() got an unexpected keyword argument 'cu_seq_lens_q'
- Issue#16Lxiangyue2025-08-12 05:26TypeError: LlavaQwenForCausalLM.forward() got an unexpected keyword argument 'cu_seq_lens_q'
- Issue#16Lxiangyue2025-08-11 14:38TypeError: LlavaQwenForCausalLM.forward() got an unexpected keyword argument 'cu_seq_lens_q'
- Pull request#15CaraJ72025-07-29 15:31
- Issue#14jaclyngu2025-07-12 18:00Reproducing issues
- Issue comment#13fake-warrior82025-07-10 08:00How to download the training set to implement your result?
- Issue comment#13CaraJ72025-07-10 07:51How to download the training set to implement your result?
- Issue#13fake-warrior82025-07-10 07:39How to download the training set to implement your result?
- Issue comment#12CaraJ72025-07-10 01:17Evaluation Code of T2I-CompBench
- Issue#11QuLiao11172025-06-18 08:08calculation of grpo loss
- Issue comment#9CaraJ72025-06-18 03:21Training Efficiency
- Issue comment#9eslambakr2025-06-17 10:56Training Efficiency
- Issue comment#10CaraJ72025-06-17 08:17There are variables in the training code that are not defined.
- Issue#10HalvesChen2025-06-17 08:12There are variables in the training code that are not defined.
- Issue comment#9CaraJ72025-06-17 05:54Training Efficiency
- Issue comment#8wtc98062025-06-10 09:09Training problem
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 337 stars here means stars gained during the window, not the repo's star count.