datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
hf-assetsevai-assets
EVAI Assets
Character, story and voice assets for subculture-style AI training and local character-chat
applications. The payload is kept here instead of in the application repository so that the
client stays small and the assets can be fetched on demand.
Contents
Path
Files
Size
Description
data/dataset/
285
31 MB
Per-character persona profiles, localized dialogue sets and intimacy patterns (JSON / JSONL)
data/eversoul-assets/
2,196
549 MB
Character… See the full description on the dataset page: https://huggingface.co/datasets/garnetrapture/evai-assets.runeterra-chill-assetshf-assetsscrapstorm-assets
Scrapstorm League assets
Meshes, PBR textures, HDRIs, audio, UI stills, and cutscene video for
MohammadSadeghSalehi/scrapstorm.
This is data, not the game. Clone the GitHub repo, then:
pip install -U huggingface_hub
node scripts/fetch-assets.mjs
Licenses are mixed (MIT originals, CC0 Poly Haven / Kenney, CC BY AmaraSpatial-10K).
See SOURCES.md and the game's NOTICE file.
Do not use these files as a generic asset dump without the game's attribution.
gawd-bavisbox-assetscomfyui-wan22-assetsgdpval-large-assetstrove-lib-documentation-assetss2s-blog-assetstts-rs-assets
tts-rs-assets
Derived assets for tts-rs: per-stage reference
activations that the Rust ports are gated against, plus two small CosyVoice artifacts that
cannot be produced without the upstream python package.
No model weights are here. You download those from their own repositories; see
docs/setup.md in tts-rs.
What is in here, and why it is not in the git repo
file
size
what it is
cosyvoice/rand_noise.safetensors
4.6 MB
The CFM decoder's fixed noise… See the full description on the dataset page: https://huggingface.co/datasets/drmhse/tts-rs-assets.my-app-assetsvideo-regen-assets
Video ReGen 媒体库
Video ReGen Recipes 的配套素材仓库。Recipes 定义「复刻什么」，ComfyUI Toolkit 负责「怎么执行」，本仓库按需提供模板运行所需的固定素材：动作驱动、默认配乐、示例角色图、已发布剪辑片段和演示母版。
这不是训练数据
本仓库存的是媒体文件，不是数据集样本。不要用它训练模型，也不要把它的存在当作上游素材的授权。
许可分层
仓库自身的清单、索引和说明可以用 MIT 理解；媒体文件不适用统一许可。角色形象、原曲、录音、字体和其他第三方内容各归其权利人，公开托管不等于授权再分发、商业使用或二次改编。每个资产记录的 provenance 字段写明了它是什么、从哪来，遇到需要授权才能用的场景，以那份说明和上游权利人的条款为准。
目录
README.md 本说明
catalog.json 机器可读总索引（资产… See the full description on the dataset page: https://huggingface.co/datasets/Shenrui-Ma/video-regen-assets.va-test-assetsautism-profile-assetsai-assetsGOSUAI-assetsbrand-assetstest-assetsmusic-mood-recs-assets
music-mood-recs — derived assets
Audio, mel-spectrograms, and embeddings for a non-commercial student deep-learning
coursework project (audio mood classification + content-based recommendation, single
CNN model). This repo exists only so the project's Streamlit demo app can fetch these
files at runtime without bundling ~7GB into the git repo.
Source & license
All audio originates from the MTG-Jamendo Dataset (mood/theme subset, 50-TAR sample,
3,585 tracks):… See the full description on the dataset page: https://huggingface.co/datasets/Ketose333/music-mood-recs-assets.assetsgithub-assetspe-av-assetsgawd-cannes2026-bavisbox-assetsAIDAS-Omni-Modal-Diffusion-assetswhoff-assetsjarvis-assetsemerald-legacy-assetsopenmontage-temp-assetsmars-cat-episode2-corrected-assets
Mars Cat Episode 2 corrected assets
Corrected character keyframes for video generation.