Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers""
Python · active 2023-11-28 → 2026-05-08 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 893 days from 2023-11-28 to 2026-05-08. Pushes: 73 total, peak 21 in a day. Pull requests: 7 total, peak 2 in a day. Issues: 63 total, peak 7 in a day. Comments: 62 total, peak 12 in a day. Stars: 926 total, peak 70 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 |
|---|---|---|---|---|
| willisma | 120 | 73 | 0 | 27 |
| xmhGit | 14 | 0 | 0 | 11 |
| zelaki | 6 | 0 | 0 | 4 |
| WANGSSSSSSS | 5 | 0 | 0 | 3 |
| stein-666 | 5 | 0 | 0 | 0 |
| iago-suarez | 4 | 0 | 2 | 2 |
| DQSSSSS | 3 | 0 | 1 | 1 |
| yifanpu001 | 3 | 0 | 0 | 1 |
| showstarpro | 2 | 0 | 2 | 0 |
| JincanDeng | 2 | 0 | 0 | 0 |
| realfolkcode | 2 | 0 | 0 | 1 |
| stefenmax | 2 | 0 | 0 | 0 |
| YuyangYin | 2 | 0 | 0 | 0 |
| zhengyunqq | 2 | 0 | 0 | 0 |
| guyuchao | 2 | 0 | 0 | 1 |
| chinmay5 | 2 | 0 | 0 | 1 |
| maxin-cn | 2 | 0 | 0 | 1 |
| LucasYFL | 2 | 0 | 0 | 1 |
| Daiver | 1 | 0 | 0 | 0 |
| weiwei-gao | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#43ZhouTimeMachine2025-12-22 02:48
- Pull request#45iago-suarez2025-12-21 10:46
- Issue comment#43iago-suarez2025-12-21 10:37fix: OOM error when sampling during training
- Issue#44Graeme-Lee2025-12-10 23:13How to sample in image space with checkpoints trained using prediction="score" or prediction="noise"?
- Issue comment#42willisma2025-11-05 03:27HF hosted SiT Checkpoints
- Issue#42willisma2025-11-04 18:51HF hosted SiT Checkpoints
- Issue#42willisma2025-11-04 18:51HF hosted SiT Checkpoints
- Issue#41Shuanglin-11262025-11-01 05:05The weight of SiT-S/B/L
- Issue#30zelaki2025-10-18 11:59regarding learn_sigma argument
- Issue#38QhelDIV2025-08-07 23:46Inconsistency between Input dimension of Model.forward and transport.training_losses
- Issue comment#34simulateuser5382025-07-05 12:53512x512 pretrained model checkpoint
- Pull request#37showstarpro2025-06-16 07:57
- Pull request#37showstarpro2025-06-16 07:56
- Pull request#36aTamaz2025-03-16 18:04
- Issue#35hiyyg2025-02-21 05:56Does it support x prediction?
- Issue#34DogyunPark2025-02-04 15:16512x512 pretrained model checkpoint
- Issue comment#21joh-schb2025-01-26 17:45The number of function evaluation (NFE) in ODE mode
- Issue#33stein-6662025-01-13 16:14The question about pretrain model
- Issue comment#31zelaki2025-01-11 20:21Performance Misaligned
- Issue comment#23maxin-cn2025-01-08 23:43Some questions about forward_with_cfg
- Issue comment#31zelaki2025-01-08 19:29Performance Misaligned
- Issue comment#26DQSSSSS2025-01-08 17:15sample_eps maybe None
- Pull request#32DQSSSSS2025-01-08 17:13
- Issue comment#31willisma2025-01-08 16:44Performance Misaligned
- Issue comment#30willisma2025-01-08 16:41regarding learn_sigma argument
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 926 stars here means stars gained during the window, not the repo's star count.