This repository contains training-video shards prepared for VideoVAE experiments. - Videos available on the packaging host: 27,351. - Each shard contains videos/partN/.mp4 and an internal manifest.jsonl. - Global manifests are under OpenViD-HD/metadata/manifests/videos-min132/. The 81--131-frame expansion is intentionally not included in this release because the complete quality-metric table needed to apply the same gates was unavailable when this subset was packaged. See OpenViD-HD/README.md for the organized videos, VAE latents, and current >=121-frame qualified selection. The older description above documents the original release. See UltraVideo/README.md for the metadata-first…
Independent publisher
MingyangWu
mingyang-wu
Models in Library0
Datasets in Library1
Models on Hugging Face1
Followers—
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Video generation.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.