Skip to content

[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation

active 2024-03-192025-07-26 (UTC)

Partial coverage16,637 / 21,066 hourly files (79%) · 2 absent upstream · 4,428 failed, retryable2024-03-172026-08-12 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
362
Pushes
4
Pull requests
4
Issues
24
Stars
284
Forks
15

Activity over time

Daily event counts in the loaded window

Line chart, 495 days from 2024-03-19 to 2025-07-26. Pushes: 4 total, peak 1 in a day. Pull requests: 4 total, peak 1 in a day. Issues: 24 total, peak 2 in a day. Comments: 31 total, peak 5 in a day. Stars: 284 total, peak 5 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 comment#106TaylorJocelyn2025-07-18 02:58
    Training loss?
  • Issue comment#77eaeful2025-06-25 18:51
    How to train stabilityai/stable-diffusion-xl-base-1.0 using ImageReward model
  • Issue#111lestersssss2025-03-07 00:46
    Unable to pin memory: operation not supported
  • Issue#110aswordok2025-03-07 00:29
    'gbk' codec can't decode byte 0xa2 in position 116
  • Issue#108deropty2025-01-19 05:09
    the vae module can not generate normal images
  • Issue#107Zhang-ZheWei2025-01-11 08:52
    我是一名深度学习新手,我尝试自己做了一个训练集并运行您的训练脚本,遇到了一些问题
  • Issue#107Zhang-ZheWei2025-01-09 07:34
    我是一名深度学习新手,我尝试自己做了一个训练集并运行您的训练脚本,遇到了一些问题
  • Issue comment#104xujz182025-01-05 08:25
    not find problem category label file corresponding to the image
  • Issue comment#99xujz182025-01-05 08:24
    Human Annotation Analysis
  • Issue comment#103xujz182025-01-05 08:19
    where i can find the train.json
  • Issue comment#101xujz182025-01-05 07:55
    数据集损坏问题
  • Issue comment#102xujz182025-01-05 07:54
    range of perference scores
  • Issue comment#105PINKRAYL2024-12-25 13:20
    self.noise_scheduler.reset_timesteps()没有reset_timesteps这个方法
  • Issue comment#101ZachL12024-12-18 02:38
    数据集损坏问题
  • Issue comment#53ZachL12024-12-18 02:37
    Dataset download issue
  • Issue comment#99ctxya12072024-12-08 07:45
    Human Annotation Analysis
  • Issue#104ctxya12072024-11-13 01:24
    not find problem category label file corresponding to the image
  • Issue#103ctxya12072024-11-01 06:26
    where i can find the train.json
  • Issue#102ctxya12072024-10-29 01:40
    range of perference scores
  • Issue#101psycho-ygq2024-10-21 05:12
    数据集损坏问题
  • Issue comment#99crisnvg2024-10-20 14:32
    Human Annotation Analysis
  • Issue comment#26psycho-ygq2024-10-20 12:35
    How to use HuggingFace Data?
  • Issue comment#100xujz182024-10-18 02:08
    fine-tuning: NotImplementedError
  • Issue comment#992927256512024-10-10 01:43
    Human Annotation Analysis
  • Issue comment#98prantikseal2024-10-03 04:44
    ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. deepseek-vl 1.0.0 requires timm>=0.9.16, but you have timm 0.6.13 which is incompatible.

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 284 stars here means stars gained during the window, not the repo's star count.