SwiftBatch Studio: limited evaluation beta

PRODUCT TEXT FONTS
DM Sans, Montserrat, Lora, Playfair Display, Cormorant Garamond, Caveat,
Dancing Script and Bebas Neue are distributed under the SIL Open Font License
1.1. Each family's copyright notice and full license are included in
licenses/FONT-<family-id>-OFL.txt. Font source URLs, file hashes and sizes are
recorded in fonts/SOURCES.json. Source: https://github.com/google/fonts
The bundled Latin webfonts are served from this site. Other scripts may use
the browser's fallback glyphs. No customer wording is sent to a font service.

OPTIONAL LOCAL BACKGROUND REMOVAL
This beta offers the experimental Detail model only. The model is downloaded
from the pinned Hugging Face URL below only after explicit consent and a
high-memory acknowledgement. Processing tools come from this site. Photos and
masks are processed in a dedicated browser worker and are never uploaded.
There is no automatic download, smaller-model fallback, or paid inference API.
The earlier Quick/U2Netp model and its implementation are not included.

DETAIL MODEL: BIREFNET-LITE-512
Original BiRefNet author: ZhengPeng (ZhengPeng7), with the BiRefNet contributors.
Browser ONNX conversion: Studio Ludens V.O.F., based on ZhengPeng7/BiRefNet_lite.
Original code: https://github.com/ZhengPeng7/BiRefNet
Original weights: https://huggingface.co/ZhengPeng7/BiRefNet_lite
Converted model: https://huggingface.co/studioludens/birefnet-lite-512
Exact model card:
https://huggingface.co/studioludens/birefnet-lite-512/blob/962e67969ec6acec9c19fab76acee4f5e22e990c/README.md
Pinned revision: 962e67969ec6acec9c19fab76acee4f5e22e990c
Pinned file: onnx/model_fp16.onnx
Download URL:
https://huggingface.co/studioludens/birefnet-lite-512/resolve/962e67969ec6acec9c19fab76acee4f5e22e990c/onnx/model_fp16.onnx
Size: 98,484,532 bytes.
SHA256: eff9216bb2f9d3f023d9c2b7196845a7485739ab1f231593633e4d2344ffc516
SwiftBatch Studio verifies this digest before creating an inference session.
The model is not bundled in this site's source or upload archive. Hugging Face
and its binary CDN receive normal download connection information, not photos.

MIT WEIGHTS LICENSE AND UNRESOLVED TRAINING-DATASET RIGHTS
The exact converted model declares MIT. Its complete license is included
unchanged at licenses/BIREFNET-LITE-MIT.txt, including:
Copyright (c) 2024 ZhengPeng
Copyright (c) 2026 Studio Ludens V.O.F.
The upstream author also reaffirmed the weights' MIT licensing:
https://github.com/ZhengPeng7/BiRefNet/issues/316#issuecomment-5120372022

The MIT notice does not resolve every training-dataset question. The upstream
author acknowledged the DIS5K dataset-license concern:
https://github.com/ZhengPeng7/BiRefNet/issues/306#issuecomment-4638021804
The dataset's own terms must be considered separately:
https://github.com/xuebinqin/DIS/blob/main/DIS5K-Dataset-Terms-of-Use.pdf
This limited evaluation beta proceeds with that uncertainty disclosed. It is
not a determination of full commercial clearance or a claim that every part of
the training-data provenance is unrestricted. Review those rights before a
commercial launch. This notice does not grant rights beyond the actual licenses.

PREPROCESSING AND OUTPUT LIMITS
Detail uses RGB at 512x512, /255 and ImageNet channel normalization, input_image
float32 input, output_image float32 logits, then sigmoid. Original image alpha
is multiplied by the resulting mask. Original files and their pixels remain
unchanged. Browser canvas resizing can differ from other inference runtimes.
The output can miss fine weave holes, glass, shadows, lid openings or edges.
Inspect important images and restore the original when the cutout is wrong.
The helper is preference guidance, not memory detection or quality certification.

ONNX RUNTIME WEB
Pinned official npm package: onnxruntime-web 1.30.0, Microsoft Corporation.
https://www.npmjs.com/package/onnxruntime-web/v/1.30.0
https://github.com/microsoft/onnxruntime
Runtime MIT license: licenses/ONNXRUNTIME-MIT.txt
Additional notices: licenses/ONNXRUNTIME-THIRD-PARTY.txt
The three runtime assets are unmodified from the official package:
- vendor/ort/ort.wasm.min.mjs: 50,126 bytes
  SHA256 219e6a1fc8a9938268d18efca3c91d310bd2f4a59bbd13744df5b2b7fc6cee3b
- vendor/ort/ort-wasm-simd-threaded.mjs: 24,381 bytes
  SHA256 e13f7f94fc51b4ca72b12faeb1ee95f4ace6dfbc8939bc718aabdc0a27c4299b
- vendor/ort/ort-wasm-simd-threaded.wasm: 14,239,897 bytes
  SHA256 3398c10d07d229bd91b364548e130e0e51a8e5704b88c7c083ebbeb78842dee2
Total Detail model plus runtime: 112,798,936 bytes (about 113 MB), before HTTP
compression. Progress counts the model and WASM (112,724,429 bytes); the two
small runtime modules add 74,507 bytes. Only the single-thread WASM backend is
used. The browser may reuse its ordinary HTTP cache; offline use is not promised.

Our Node WASM validation used around 2.5 GB process memory and about 10 seconds
per photo for Detail. This is not a phone benchmark. A low-memory tab may reload
or close and lose its in-page batch. No phone compatibility is certified.

SAMPLE PHOTOGRAPHS AND PREPARED CUTOUT
See samples/ATTRIBUTION.txt for the licensed collection photographs, the CC0
legacy walkthrough original and the retained legacy prepared cutout. The collection
preview and guided walkthrough use real photographs with their original backgrounds;
they perform canvas framing, text and styling, not background removal. Optional
studio inference asks permission. No photographer or depicted product endorses SwiftBatch Studio.

ACOUSTIC PIANO RECORDINGS
Versilian Community Sample Library — Kawai Grand Piano, by Versilian Studios LLC.
Source: https://github.com/sgossner/VCSL
Revision: c1ea7bcc3c7309650ab0da9d15c9cd1fbc4a4c7e
CC0 1.0 Universal: licenses/VCSL-CC0.txt
Selected soft velocity, player-perspective samples C2, F#2, C3, F#3, C4.
Modified for SwiftBatch Studio: trimmed to 4.5 seconds, reduced low-frequency rumble,
converted to 22.05 kHz mono PCM16, level normalized, faded tails.
Five local files total 992,470 bytes. Loaded only when music is requested.
SwiftBatch Studio's melodies are original; the piano timbre comes from these recordings.

BUTTON TAP
Kenney — Interface Sounds, click_001.ogg, CC0 1.0 Universal.
Source: https://kenney.nl/assets/interface-sounds
License notice: licenses/KENNEY-INTERFACE-CC0.txt
Modified for SwiftBatch Studio: softened high frequencies and low rumble, trimmed,
converted to mono 22.05 kHz PCM16, level normalized, short fades.
Embedded as compact PCM in button-click.js to avoid a delayed audio download.
The tap plays at a fixed, quiet level, independently of the music slider.

PIP'S SPOKEN WELCOME
Original SwiftBatch Studio script, synthesized locally with Kokoro v1.0, am_puck voice.
The opening phrase blends am_puck (35%) and am_michael (65%) with calmer
punctuation; the remainder uses am_puck with the updated SwiftBatch Studio name.
Model: https://huggingface.co/hexgrad/Kokoro-82M
Inference tooling: https://github.com/thewh1teagle/kokoro-onnx
Apache 2.0 model license: licenses/KOKORO-APACHE-2.0.txt
The site serves only the finished mono MP3. No speech model or third-party
speech service runs in visitors' browsers. The voice is AI generated.

PIP DEMO NARRATION
The audio/demo-pip-*.mp3 clips use the same locally generated Kokoro am_puck voice as Pip's spoken welcome. These are prerecorded clips; no voice model or speech service runs in the browser. The model and voice licensing and attribution above also apply to these clips.