Skip to content

active 2024-12-232025-08-05 (UTC)

Partial coverage12,581 / 14,303 hourly files (88%) · 2 absent upstream · 1,716 failed, retryable2024-12-232026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
138
Pushes
10
Pull requests
0
Issues
16
Stars
95
Forks
2

Activity over time

Daily event counts in the loaded window

Line chart, 226 days from 2024-12-23 to 2025-08-05. Pushes: 10 total, peak 3 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 16 total, peak 3 in a day. Comments: 15 total, peak 5 in a day. Stars: 95 total, peak 4 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
QuLiao111720909
tianzhangwu10004
HalvesChen5002
invoker-LL2000
cpaaax1000
silvercherry1000
lavinal7121000

Recent activity

Latest issues, pull requests and releases

  • Issue#27HalvesChen2025-07-26 03:37
    W/O MSVQ version
  • Issue#25HalvesChen2025-01-17 02:56
    About img_size
  • Issue comment#24QuLiao11172025-01-16 06:34
    CLIP ViT-B/14 in the paper, but ViT-B/16 in the code.
  • Issue#24tianzhangwu2025-01-16 03:48
    CLIP ViT-B/14 in the paper, but ViT-B/16 in the code.
  • Issue#21tianzhangwu2025-01-15 06:37
    About inference image resolution
  • Issue#22tianzhangwu2025-01-15 06:37
    The reconstruction loss increases when adding discriminator loss
  • Issue#18QuLiao11172025-01-13 02:28
    about OCR reconstruction
  • Issue comment#19HalvesChen2025-01-11 08:56
    Training data for tokenizer
  • Issue comment#19HalvesChen2025-01-10 05:53
    Training data for tokenizer
  • Issue#20tianzhangwu2025-01-10 03:37
    About face data
  • Issue comment#19QuLiao11172025-01-10 03:20
    Training data for tokenizer
  • Issue#19HalvesChen2025-01-10 01:52
    Training data for tokenizer
  • Issue#16QuLiao11172025-01-08 07:52
    How to control feature input strategies in the released code?
  • Issue comment#16tianzhangwu2025-01-08 07:51
    How to control feature input strategies in the released code?
  • Issue comment#16QuLiao11172025-01-08 07:30
    How to control feature input strategies in the released code?
  • Issue#17tianzhangwu2025-01-08 07:26
    Is there a timetable for single-scale version of TokenFlow?
  • Issue comment#16tianzhangwu2025-01-08 07:22
    How to control feature input strategies in the released code?
  • Issue comment#16tianzhangwu2025-01-08 07:08
    How to control feature input strategies in the released code?
  • Issue comment#16QuLiao11172025-01-08 06:51
    How to control feature input strategies in the released code?
  • Issue#11cpaaax2025-01-08 02:28
    Release the single-scale version of TokenFlow B/L
  • Issue#15lavinal7122025-01-07 02:52
    The direct application of this method to VAE
  • Issue comment#14QuLiao11172025-01-06 07:05
    The final input to the LLM is still a continuous feature representation for i2t
  • Issue comment#14tianzhangwu2025-01-06 06:51
    The final input to the LLM is still a continuous feature representation for i2t
  • Issue comment#14QuLiao11172025-01-06 06:45
    The final input to the LLM is still a continuous feature representation for i2t
  • Issue#14tianzhangwu2025-01-06 06:34
    The final input to the LLM is still a continuous feature representation for i2t

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 95 stars here means stars gained during the window, not the repo's star count.