Skip to content

国产图像AI

active 2025-04-062026-05-13 (UTC)

Partial coverage11,343 / 12,181 hourly files (93%) · 2 absent upstream · 835 failed, retryable2025-03-212026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
1.3K
Pushes
6
Pull requests
5
Issues
28
Stars
1.1K
Forks
112

Activity over time

Daily event counts in the loaded window

Line chart, 403 days from 2025-04-06 to 2026-05-13. Pushes: 6 total, peak 1 in a day. Pull requests: 5 total, peak 1 in a day. Issues: 28 total, peak 3 in a day. Comments: 74 total, peak 16 in a day. Stars: 1,110 total, peak 135 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

Recent activity

Latest issues, pull requests and releases

  • Issue#74wjq9206152025-10-20 07:20
    how can i run demo case in A100-40G environment?
  • Issue comment#70KernelInterrupt2025-07-24 00:36
    sample code does not run
  • Issue comment#70ictzyqq2025-07-21 01:58
    sample code does not run
  • Issue#69libai-lab2025-07-16 15:59
    Thank you for your excellent work. May I ask how much VRAM is needed to run your latest image editing model. How long does it take to generate a single image, and how does it compare to support multi image editing and flux kontext?
  • Pull request#68raviautar2025-07-14 09:37
  • Issue#67lzyhha2025-07-14 07:56
    The way to apply attention mask.
  • Issue#65Mulanss2025-07-09 09:00
    Use .expand() instead of .repeat() to avoid unnecessary memory allocation in scatter_reduce_ index construction
  • Issue#64gangxu8222025-07-03 14:31
    hi,能够支持生成影子吗
  • Issue comment#50eaeful2025-06-20 09:09
    Tech report
  • Issue comment#60nitinh122025-06-04 07:43
    No Automatic1111 or Forge WebUi?
  • Issue comment#63StrongerXi2025-05-30 20:29
    Decrease Inference time with torch.compile
  • Issue comment#19AlexNolasco2025-05-28 03:32
    Any plans for tools like fill, redux
  • Issue#62camoody12025-05-26 15:36
    HiDream Dev Inpaint Model?
  • Issue comment#22akierum2025-05-25 19:42
    Run on multiple GPUs
  • Issue comment#39eaeful2025-05-25 08:14
    The fastest way to build an ecosystem is to open up lora train as soon as possible.
  • Issue#61Me-verner2025-05-19 00:46
    Model loading takes too long — any way to speed it up?
  • Issue#60aiartalchemy2025-05-16 01:17
    No Automatic1111 or Forge WebUi?
  • Issue comment#59pomyin2025-05-15 03:05
    ComfyUI 是官方支持 HiDream 了,但出图效果这么烂,官方不沟通一下?或提供一些技术支持?
  • Issue comment#56Tammytcl2025-05-13 03:33
    Suggestion: TaylorSeer Acceleration for HiDream-I1 in README
  • Issue#59wikeeyang2025-05-13 03:33
    ComfyUI 是官方支持 HiDream 了,但出图效果这么烂,官方不沟通一下?或提供一些技术支持?
  • Issue comment#56philipy12192025-05-13 03:31
    Suggestion: TaylorSeer Acceleration for HiDream-I1 in README
  • Issue comment#56IM-0012025-05-09 03:35
    Suggestion: TaylorSeer Acceleration for HiDream-I1 in README
  • Issue comment#22gaestur2025-05-07 05:18
    Run on multiple GPUs
  • Pull request#57accomolate2025-05-07 01:37
  • Issue comment#56Shenyi-Z2025-05-04 08:50
    Suggestion: TaylorSeer Acceleration for HiDream-I1 in README

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1,110 stars here means stars gained during the window, not the repo's star count.