Consistency Distillation with Target Timestep Selection and Decoupled Guidance
active 2024-08-21 → 2025-09-16 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 392 days from 2024-08-21 to 2025-09-16. Pushes: 53 total, peak 8 in a day. Pull requests: 6 total, peak 2 in a day. Issues: 22 total, peak 2 in a day. Comments: 20 total, peak 3 in a day. Stars: 87 total, peak 17 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 |
|---|---|---|---|---|
| WangCunzheng | 33 | 29 | 0 | 4 |
| RedAIGC | 13 | 8 | 2 | 3 |
| fastisrealslow | 12 | 8 | 2 | 2 |
| Ldhlwh | 7 | 7 | 0 | 0 |
| bigmover | 6 | 0 | 0 | 2 |
| lovejing0306 | 4 | 0 | 0 | 2 |
| solitaryTian | 4 | 0 | 0 | 1 |
| JayChen7777 | 2 | 0 | 2 | 0 |
| Gforky | 2 | 0 | 0 | 2 |
| LaFeuilleMorte | 1 | 0 | 0 | 0 |
| YangYang-DLUT | 1 | 0 | 0 | 0 |
| XiaXin-Aloys | 1 | 0 | 0 | 0 |
| huangjun12 | 1 | 0 | 0 | 1 |
| solveopt | 1 | 0 | 0 | 0 |
| sourceful-wing | 1 | 0 | 0 | 1 |
| ZhengMengbin | 1 | 0 | 0 | 0 |
| xuchen-dev | 1 | 0 | 0 | 0 |
| RuiJZ | 1 | 0 | 0 | 1 |
| Hzj199 | 1 | 0 | 0 | 0 |
| palmerkuo | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#19RuiJZ2025-08-29 03:20train flux loss is Nan
- Issue#23LaFeuilleMorte2025-07-03 08:06Training dataset
- Issue#21haoyan142025-06-10 02:48flux 辨别器forward bug
- Issue#20solveopt2025-04-25 08:38why use decouple guidance instead of cfg distillation
- Issue#19chenyu202307022025-04-24 02:19train flux loss is Nan
- Issue comment#17Gforky2025-04-07 12:26version of diffusers
- Issue comment#15Gforky2025-04-07 10:05Size not match for 'packed_noisy_model_input' and 'latent_image_ids'.
- Issue comment#2huangjun122025-03-06 10:46FLUX infer code is missing
- Issue comment#18fastisrealslow2025-02-10 09:50checkpoint has error key
- Issue comment#18WangCunzheng2025-02-10 09:38checkpoint has error key
- Issue comment#18fastisrealslow2025-02-10 09:33checkpoint has error key
- Issue#18xuchen-dev2025-02-06 10:48checkpoint has error key
- Issue#17solitaryTian2025-02-06 07:18version of diffusers
- Issue#16solitaryTian2025-02-05 06:38'FrozenDict' object has no attribute 'use_flow_sigmas'
- Issue comment#6sourceful-wing2025-01-27 22:26Training cost on FLUX
- Issue comment#6solitaryTian2025-01-26 02:29Training cost on FLUX
- Issue#15solitaryTian2025-01-20 06:56Size not match for 'packed_noisy_model_input' and 'latent_image_ids'.
- Issue#14rong79322025-01-08 18:30手部崩坏问
- Pull request#13fastisrealslow2025-01-04 06:54
- Pull request#13JayChen77772024-12-30 02:16
- Pull request#12fastisrealslow2024-12-26 07:15
- Pull request#12JayChen77772024-12-21 07:50
- Issue#11duzhixing2024-11-26 06:18Training loss reduction log
- Issue#7bigmover2024-11-06 02:27whether is γ-sampler not quite consistent with the formulas in the paper?
- Issue comment#7bigmover2024-11-06 02:11whether is γ-sampler not quite consistent with the formulas in the paper?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 87 stars here means stars gained during the window, not the repo's star count.