Skip to content

adobe-research/custom-diffusion

View on GitHub ↗Related repositories →

Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)

active 2023-08-242026-05-24 (UTC)

Partial coverage20,304 / 26,045 hourly files (78%) · 2 absent upstream · 5,738 failed, retryable2023-08-232026-08-12 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
416
Pushes
5
Pull requests
0
Issues
22
Stars
314
Forks
29

Activity over time

Daily event counts in the loaded window

Line chart, 1005 days from 2023-08-24 to 2026-05-24. Pushes: 5 total, peak 1 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 22 total, peak 2 in a day. Comments: 46 total, peak 6 in a day. Stars: 314 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#98chenyangzhu12024-10-11 07:56
    retrieve.py question
  • Issue comment#96nupurkmr92024-08-04 17:25
    Is this version trained with lora?
  • Issue comment#89aniket0042024-07-22 22:30
    Is it possible to train multi joint training with SDXL? diffusers_training_sdxl.py seems impossible for multi joint training.
  • Issue comment#98chenjingcheng2024-06-29 14:16
    retrieve.py question
  • Issue comment#35yoon282024-06-12 02:33
    retrieve.py doesn't work
  • Issue comment#35kuailexiaohunzi2024-06-12 02:24
    retrieve.py doesn't work
  • Issue comment#35yoon282024-06-12 00:57
    retrieve.py doesn't work
  • Issue comment#92VernalXu2024-04-15 05:50
    Does the diffusers version now work properly?
  • Issue comment#91Shentao-YANG2024-04-01 00:44
    Missing text prompts?
  • Issue#91Shentao-YANG2024-04-01 00:44
    Missing text prompts?
  • Issue comment#95nupurkmr92024-03-31 21:37
    Unable to retrieve the image used for regularization.
  • Issue comment#93nupurkmr92024-03-31 21:35
    why the results produced by the model training and verification are inconsistent with the results I test using the saved model weights?
  • Issue comment#91nupurkmr92024-03-31 21:34
    Missing text prompts?
  • Issue comment#90nupurkmr92024-03-31 21:28
    Question about loss on valid image region during training
  • Issue comment#89nupurkmr92024-03-31 21:26
    Is it possible to train multi joint training with SDXL? diffusers_training_sdxl.py seems impossible for multi joint training.
  • Issue comment#92aishwarymishra092024-03-31 21:02
    Does the diffusers version now work properly?
  • Issue#93baimazhaoge2024-03-25 01:01
    why the results produced by the model training and verification are inconsistent with the results I test using the saved model weights?
  • Issue comment#73nrsz000112024-03-24 11:47
    Plan for integration of SDXL? It seems to require more work than changing the MODEL_NAME
  • Issue comment#32digbangbang2024-03-07 06:24
    time out when connect to laion.ai
  • Issue#92wsfk7162024-03-02 12:05
    Does the diffusers version now work properly?
  • Issue#91Shentao-YANG2024-02-21 06:08
    Missing text prompts?
  • Issue#70aatiibutt2024-02-02 22:49
    How to Visualize Attention Maps to Analyze Compositions?
  • Issue comment#88nupurkmr92024-02-01 01:57
    why my optimization based weights merging is not work?
  • Issue comment#88ZZZBBBZZZ2024-01-30 07:30
    why my optimization based weights merging is not work?
  • Issue comment#88zaczywy2024-01-30 07:28
    why my optimization based weights merging is not work?

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 314 stars here means stars gained during the window, not the repo's star count.