LAION AI
@laion-ai • This is the repo of LAION, a non-profit organization to liberate machine learning research, models and datasets.. Use this route to separate flagship concentration from portfolio breadth before you treat a publisher as broadly strong.
Portfolio concentration
40%
Top three share
Shows whether the organization is driven by one breakout repo or several visible projects.
Breadth
28 repos
Visible snapshot
28 repositories updated in the last 90 days.
Leading language
Unknown
Portfolio mix
Unknown (14), HTML (10), Python (4)
Average size
0
Stars per repository
Useful for distinguishing one flagship-heavy publisher from a repeatable portfolio.
Updated: 2026-08-26(4h ago)GitHub API fallback28 repositories
40%
of the visible star count comes from this organization's top three repositories.
0
stars per repository in this same snapshot.
Unknown
is the most common language here, with 28 repositories updated in the last 90 days.
Why this rank
This organization stands out because its public portfolio is relatively balanced across 28 repositories.
Balanced portfolio across 28 reposTop 3 share 40%
Organization pages work best when you separate portfolio breadth from flagship concentration. In LAION AI's case, the visible top three repositories account for about 40% of total stars in this snapshot, which helps explain whether the organization is known for one breakout project or for a broader repeatable portfolio.
The dominant language mix here is Unknown (14), HTML (10), Python (4). That makes this page useful not just for popularity checks, but also for seeing what technical shape an organization's public ecosystem actually has.
Top Repositories
| # | Repository | Language | Stars |
|---|---|---|---|
| 1 | laion-ai/open-sci-ref-0.02 Readme pointing to the open-sci-ref-0.02 release in LAION-AI/open-sci-ref | 2 | |
| 2 | laion-ai/open_clip_video_autoexp | Python | 1 |
| 3 | laion-ai/moss-voice-profiles-converted MOSS voice-profile matrix, all clips converted to one target voice (emolia_c1675) via Chatterbox VC | 1 | |
| 4 | laion-ai/moss-voice-clustering-analysis How many voice clusters are really there? Cluster-structure analysis of the 6064 MOSS reference voices. | 1 | |
| 5 | laion-ai/moss-voice-profiles Conditioned speech corpus generator: 808 conditions per voice, EN+DE paired, with demo grid | HTML | 1 |
| 6 | laion-ai/moss-mediathek-reinterpreted-voices Reinterpreted German reference voices (Mediathek-derived, synthetic) | 1 | |
| 7 | laion-ai/moss-reference-voice-search Reference-voice search demo — 1336 Gemini-annotated character voices, semantic + BM25 search | Python | 1 |
| 8 | laion-ai/voice-acting-search-agent Autonomous LLM-driven search agent for LoRA+prompt strategies on MOSS-VA-v2 voice acting TTS | Python | 1 |
| 9 | laion-ai/moss-voiceacting-manual MOSS-VA-v2 conditioning manual: 40 emotions (best prompt + LoRA merge %, reward, correlations) — MD skill + HTML | HTML | 1 |
| 10 | laion-ai/school-bud-e-openrouter School Bud-E is an intelligent and empathetic learning assistant designed to revolutionize the educational experience. | 0 | |
| 11 | laion-ai/bud-e-openrouter A general human-ai interaction platform. | 0 | |
| 12 | laion-ai/storytree | Python | 0 |
| 13 | laion-ai/moss-reference-voice-taxonomy | 0 | |
| 14 | laion-ai/moss-acting-casting MOSS voice-acting: Hollywood casting-session agent runs — multi-part 30s performances, speaker continuity, prompts and scores per take | 0 | |
| 15 | laion-ai/moss-reinterpreted-voices 1000 reinterpreted reference voices (cluster->SIDON->pitch->MOSS reinterpretation) | 0 | |
| 16 | laion-ai/moss-reference-reinterpretation-beforeafter Reference-voice reinterpretation before/after preview | 0 | |
| 17 | laion-ai/moss-reinterpretation-dataset-preview Voice reinterpretation training-data preview (original + top-10 expressive re-performances, procedural captions + scores) | 0 | |
| 18 | laion-ai/moss-pitch-distortion-grid ±10% pitch-shift before/after grid for reference-voice de-identification | 0 | |
| 19 | laion-ai/moss-50k-voice-search VoiceCLAP text->audio search over 50k annotated voice samples | 0 | |
| 20 | laion-ai/moss-voicenet-manual MOSS-VA-v2 VoiceNet dimension-LoRA conditioning manual (dose-response, side-effects, audio) | HTML | 0 |
| 21 | laion-ai/acting-edge-cases 266 voice-acting edge cases: coaching notes, acoustic signatures and detector tokens for expressive-speech generation and annotation | 0 | |
| 22 | laion-ai/moss-voicenet-highlow-grid VoiceNet dimension LoRAs — high vs low contrast grid | HTML | 0 |
| 23 | laion-ai/emotion-voice-conditions Emotion x voice x delivery-condition study on MOSS-TTS voice-acting: 6 voices, 40 emotions, 4 conditions, best-of-32. | HTML | 0 |
| 24 | laion-ai/character-voice-clusters Character voice clusters — VoiceNet embedding + age/background buckets, procedural captions | HTML | 0 |
| 25 | laion-ai/vocal-burst-classifier-v2 Vocal Burst Classifier V2 — 83-class non-speech vocalization classifier (LAION). Demo + docs. | HTML | 0 |
| 26 | laion-ai/moss-voicenet-lora-evolution VoiceNet-dimension LoRA evolution: 50% vs 100% dose + optimal prompting (10 generations) | HTML | 0 |
| 27 | laion-ai/moss-emotion-evolution-all Evolutionary maximization of all 40 emotions (10 generations, mean-of-8) | HTML | 0 |
| 28 | laion-ai/moss-emotion-edgecase-evolution Evolutionary edge-case search: extreme vocalizations per emotion LoRA | HTML | 0 |
Next step after the organization read
Open a flagship repository, compare a couple of portfolio leaders, or return to the organization map when you want a broader concentration read.
Learn and methodology
Keep trust-building context reachable, but behind the first data read instead of ahead of it.
How to read this organization snapshot
Total stars are useful as a discovery signal, but they do not tell you whether a team maintains every repository equally. Pair this page with release cadence, maintainer activity, and the flagship concentration shown above before making adoption decisions.
For broader background on GitStar's ranking logic and editorial guidance, see Methodology & Editorial Standards.