kevinqz/LingBot-Video-Dense-1.3B-VAE-Streaming-CoreAI

Canonical: kevinqz/LingBot-Video-Dense-1.3B-VAE-Streaming-CoreAI — source of truth.

LingBot-Video Dense 1.3B VAE (streaming) (fabric)

An Apple Core AI conversion of the VAE decoder — the AutoencoderKLWan decode path, mapping a video latent to pixel frames from robbyant/lingbot-video-dense-1.3b. Produced by coreai-fabric and indexed by coreai-catalog.

One component, not the full video pipeline. A video diffusion model is separable blocks — text encoder, VAE encoder, denoising DiT, and VAE decoder. This asset is ONLY the decoder (latent → pixels). The host owns the text encoder, the DiT few-step denoise loop, latent un-normalization (latents_mean/latents_std), frame assembly, and the streaming cache. It does not, by itself, generate video from a prompt.

Model facts

Field	Value
Parameters (upstream)	1.3B
Architecture	diffusion
Capabilities	text-to-video
Deployable core	AutoencoderKLWan VAE decoder (latent → frames)
Decoded frame shape	1×3×4×128×128
Quantization / precision	none / float32
On-disk size	280 MB
Asset kind	single-graph VAE decoder (first-chunk decode)
assetVersion	2.0

Use it — this needs host code you supply

The bundle is a single static-size graph: z (video latent) in → frames out (spatial 8× / temporal 4× upsampling, first-chunk decode). You supply the DiT denoise loop, latent un-normalization, and frame assembly in your host code (Swift or Python).

pip install coreai-catalog && coreai-catalog install lingbot-video-dense-1.3b-vae-streaming

Requirements

• Deployment: macOS 27.0+ / iOS 27.0+, Xcode 27+. The asset serializes with minimum_os v27, so the on-device Swift runtime requires macOS/iOS 27+. A Mac on macOS 26 can convert and inspect it but not run it on-device.
• Apple Silicon.

Verification (output parity)

• Gate A (structure): passed — the bundle's layout + metadata were validated; the graph loads.
• Gate B — graph_output_cosine: 1.000000 min output cosine (median 1.000000) vs the fp32 torch VAE decoder over 8 seeded latents, measured on apple_silicon. Certifies the export computes the SAME output as the source — a conversion-fidelity metric, not end video quality.
• This certifies the export is numerically faithful to the source VAE decoder — it does NOT certify end video quality. Reproduce with coreai-fabric verify.

Provenance

Field	Value
Base model	robbyant/lingbot-video-dense-1.3b @ f9789a7d9b4772a47aba62d4eb5282ddefd1da21
Converted by	models/lingbotvideo/vae_streaming_export.py (version not reported)
Recipe	lingbot-video-dense-1.3b-vae-streaming (recipe_source: fabric)
Precision / quantization	float32 / none
Conversion date	2026-07-09

Machine-readable, in this repo: parity-report.json · reproduce-manifest.json · LICENSE.

License and attribution

Weights licensed apache-2.0 — see the bundled LICENSE. This artifact is a converted derivative of the base VAE: its weights were converted to Apple Core AI format. The conversion itself is community work.

Links

• Base model: robbyant/lingbot-video-dense-1.3b
• Reproduce: recipe lingbot-video-dense-1.3b-vae-streaming
• Index: coreai-catalog
• HF Collection

The on-device Core AI ecosystem

• coreai-fabric — the reproducible recipe → .aimodel pipeline that produced this asset.
• coreai-catalog — the index of Core AI models with provenance and integration snippets.
• apple/coreai-models — Apple's official exporters and runtimes.

Not affiliated with Apple

Community conversion. Not produced, hosted, or endorsed by Apple. Apple and Core AI are trademarks of Apple Inc., used here only to describe the target runtime/format.