text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023) ai apasltd
active 2023-08-15 → 2025-07-27 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 713 days from 2023-08-15 to 2025-07-27. Pushes: 265 total, peak 13 in a day. Pull requests: 249 total, peak 9 in a day. Issues: 1,043 total, peak 32 in a day. Comments: 1,907 total, peak 48 in a day. Stars: 8,356 total, peak 836 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 |
|---|---|---|---|---|
| zRzRzRzRzRzRzR | 1.3K | 221 | 160 | 577 |
| OleehyO | 108 | 32 | 11 | 50 |
| tengjiayan20 | 80 | 5 | 2 | 72 |
| glide-the | 30 | 0 | 14 | 16 |
| yjhong89 | 28 | 0 | 0 | 9 |
| cdfan0627 | 27 | 0 | 0 | 20 |
| LittleNyima | 27 | 0 | 2 | 17 |
| yzy-thu | 26 | 2 | 0 | 23 |
| a-r-r-o-w | 24 | 0 | 0 | 24 |
| rodjjo | 20 | 0 | 5 | 12 |
| lijain | 20 | 0 | 0 | 18 |
| nitinmukesh | 20 | 0 | 0 | 16 |
| Yuancheng-Xu | 19 | 0 | 0 | 11 |
| linwenzhao1 | 18 | 0 | 0 | 9 |
| schhaohao | 18 | 0 | 0 | 6 |
| trouble-maker007 | 18 | 0 | 0 | 11 |
| xvjiarui | 18 | 0 | 0 | 11 |
| asmocklo | 18 | 0 | 0 | 18 |
| wmm-coding | 17 | 0 | 0 | 12 |
| FurkanGozukara | 16 | 0 | 0 | 9 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#787Vickeyhw2025-07-23 02:40train lora on cogvideox1.5-i2v-5b OOM
- Issue#787Vickeyhw2025-07-23 02:40train lora on cogvideox1.5-i2v-5b OOM
- Issue#787Vickeyhw2025-07-23 02:13train lora on cogvideox1.5-i2v-5b OOM
- Issue comment#761treasan2025-07-18 15:35Summary of CogVideoX-5B-I2V-v1.5 inference and fine-tuning about `vae_scaling_factor_image` and vertical video
- Issue comment#783lty22262622025-07-13 08:38📣 [Feature Update] ✨ REAL DDIM Inversion ✨ is now possible on CogVideoX!
- Issue#785sigma-alpha-beta2025-07-04 03:49finetune时grad_norm非常小
- Issue comment#680nnsriram272025-06-24 22:33CogVideoX-5B-I2V生成更長秒數影片問題
- Issue comment#748nnsriram272025-06-24 22:23Problematic result
- Issue comment#510MaxHeuillet2025-06-17 20:54ValueError: Trying to set a tensor of shape torch.Size([3072, 128]) in "weight" (which has shape torch.Size([3072, 16, 2, 2])), this looks incorrect.
- Issue comment#776jasper0314-huang2025-06-15 23:15示例脚本运行报错
- Issue comment#194apihmnizann2025-06-06 04:30Work plan and enhancement / 工作计划和用户诉求
- Issue#780MaulanaYusufIkhsanRobbani2025-06-03 10:24Validation Scheme
- Issue comment#774emmanuel-ferdman2025-06-02 18:37Resolve Python Logger warnings
- Issue#779zhangfang092025-05-30 02:19两张卡跑模型一张卡干活？
- Issue comment#663thbupt2025-05-29 03:57prepare_rotary_positional_embeddings training and inference are different
- Issue comment#774emmanuel-ferdman2025-05-26 12:16Resolve Python Logger warnings
- Issue#776zhangfang092025-05-23 03:58示例脚本运行报错
- Issue#775MaulanaYusufIkhsanRobbani2025-05-22 20:01Fail to unscale FP16 Gradients
- Pull request#774emmanuel-ferdman2025-05-14 13:24
- Issue comment#771MaulanaYusufIkhsanRobbani2025-05-14 06:14Finetune CogVideoX-5B (not 1.5) T2V takes 3 hours for 1 step using 4090
- Issue comment#771MaulanaYusufIkhsanRobbani2025-05-13 15:54Finetune CogVideoX-5B (not 1.5) T2V takes 3 hours for 1 step using 4090
- Issue comment#765snowflakewang2025-05-12 06:21Tensorboard logs seem to fail when multi-gpu training
- Issue comment#765OleehyO2025-05-12 02:46Tensorboard logs seem to fail when multi-gpu training
- Issue comment#767OleehyO2025-05-12 02:40return torch._C._nn.upsample_nearest3d(input, output_size, scale_factors) RuntimeError: "upsample_nearest3d_out_frame" not implemented for 'BFloat16'
- Issue comment#768OleehyO2025-05-12 02:37Can generate short caption?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 8,356 stars here means stars gained during the window, not the repo's star count.