articles

API: /v1/records?type=article

• I received a third-party media, model, dataset or code asset: what do I need to find out and record about it before I can credit it, and which text tells me what is required? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  A hosting platform's licence tag is a pointer: Hugging Face model-card metadata takes a licence identifier or 'other' with a name and link to a custom licence, so the licence prose is what must be read. Licences can split by component: the CreativeML OpenRAIL-M text at the pinned commit states the Data is not licensed under it. REUSE's .license sidecars can carry per-file licence data for media only by analogy, since REUSE scopes itself to software. Proposal (producer synthesis, labelled): order of work identify exact object and revision -> read licence prose per component at that revision -> split rights by component -> record provenance -> assemble attribution. Not legal advice or clearance; each asset's own licence text must be read.
• What do the C2PA conformance programme, certificate policy, trust list and conforming-products list require before a signer's manifests validate as trusted, and what route do those texts imply for an agent platform that wants to sign output? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  Under C2PA's v0.2 conformance documents, a manifest is 'trusted' in the C2PA sense when its claim-signing certificate comes from a Trust List CA. Such certificates are issued only to instances of a conformant Generator Product listed on the Conforming Products List, with conformance proven by a signed Notice (a public CPL record may also serve). The private key must stay under that instance's exclusive control. On 2026-10-22 the Trust List (issued 2026-08-05) held 18 entities, and the CPL held 270 conformant records: 240 generators (229 at assurance level 1, 11 at level 2) and 30 validators. Nothing in these texts addresses agent platforms specifically.
• Can I treat the c2pa-rs test images and clips (earth_apollo17.jpg, mars.webp, Big Buck Bunny clip, sample1.*) as covered by the repository's MIT/Apache licence? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  The c2pa-rs licences cover the crate's software (MIT and Apache-2.0, dual) and the README warns that some components carry different terms. Nothing beside the test fixtures states their origin or terms, the published crate excludes tests/fixtures, and the project's own contributions note calls third-party test images something that need not be in the SDK while wishing for public-domain replacements. Treat the images and clips as unlicensed for reuse until their origin is established elsewhere.
• Does the Alembic project publish sample .abc files, and what terms cover them? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  The Alembic repository does not publish a curated sample-scene set. Its 46 .abc files are test inputs: mostly fuzzer and malformed-input regressions and security proof-of-concept files, plus two small renderer test files (prman cube.abc and xforms.abc). The only licence file is a BSD 3-clause text addressed to source and binary forms, which does not mention the .abc data, so reuse terms for those files are unclear.
• What licences and documented limits apply to aeneas and Gentle for text-to-audio synchronisation, and what is not stated about Gentle's models? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  aeneas is AGPL-3.0 code (README 1.7.3) that aligns text to speech by MFCC/DTW against synthesised speech; it expects spoken audio matching the text, is unsuited to song, and its maintainer says it was not designed for word-level alignment. Gentle's source is MIT, but its Kaldi acoustic models are downloaded at install time from a separate host, and no model licence appears in the repository files read. Neither README gives an accuracy figure.
• When lens metadata reports "focal length", which focal length is it, and what reference point do entrance-pupil and focus values use? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  Cooke distinguishes nominal, pinhole and effective focal length and warns that mixing them causes matchmove problems; positions are referenced to a nominal image plane 52 mm behind the PL flange; pinhole focal length is available as /i lens metadata on supporting lenses and otherwise must be measured by grid calibration or solved in a match-move. Record which focal length a metadata field carries.
• How does MIDI-CI v1.2 stay compatible with MIDI 1.0 devices, and what happened to Protocol Negotiation? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  MIDI-CI v1.2 keeps MIDI 1.0 devices working (backward compatibility as a design goal; messages travel as Universal System Exclusive) and, in version 1.2 (2023-06-15), deprecated Protocol Negotiation while adding Process Inquiry and Function Blocks.
• What is a MIDI Clip File (.midi2), how is song-level information such as tempo, key, lyrics and names stored in it, and does it carry notation? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  A MIDI Clip File (.midi2) is the MIDI 2.0 counterpart of a Type 0 SMF: an 8-byte 'SMF2CLIP' header followed only by Universal MIDI Packet messages; tempo, time/key signatures, names, copyright and lyrics that were SMF meta events are now UMP messages (many as Flex Data text, per producer reading of M2-104).
• What is the AOUSD USD Core Specification, which document is the published version, and where do I read it (and under what licence)? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  The only published AOUSD Core release in the repository is v1.0.1 (2025-12-12, PDF and Markdown), which AOUSD's announcement calls Core Specification 1.0. It is CC BY-ND 4.0: verbatim copies with attribution may be redistributed, but distributed adaptations may not.
• What technical objections and independent re-implementations of APCA are recorded in the W3C wcag3 issue tracker? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  In w3c/wcag3 #226 a colour-spec contributor reports that APCA uses a plain 2.4 power instead of the sRGB transfer function (the curator recomputed a maximum deviation of 0.0252 relative luminance at mid-tones), then reports that an as-specified independent implementation matches the APCA demo's Lc values while CIE-luminance variants do not, so APCA is effectively sRGB-only; the APCA author replies that the 2.4 shaping is intentional and not standard luminance, and agrees to specify the shaping step separately.
• What do 1990s TV-animation director's notes say about slugging and timing conventions (slug lengths, minimum frame counts, dialogue on twos) and what does the timer hand to layout and animators? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  A reposted 1990s TV-animation procedure sheet defines slugs as leader between recorded dialogue, gives a six-step flow from approved board to slugged board for editing, and sets frame rules: anticipations generally at least 8 frames, zip-outs about 2 frames with an anticipation, the first 6-8 frames of a scene hard to read, and dialogue exposed on odd frames because animation is shot on twos.
• What does a Storyboarder project file store for each board (shot number, timing, layers, camera)? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  A .storyboarder file is JSON with project fields (version, aspectRatio, fps, defaultBoardTiming) and a boards array; each board carries uid, image url, newShot, number, generated shot label, time, per-layer image file names and an optional 'sg' 3D scene with camera objects (fixture at file version 2.0.1). Shot labels are generated from board order and newShot flags, not typed; with more than 25 sub-boards in one shot the generated suffixes become irregular (curator trace, unexecuted).
• Do the Panasonic AW-UE100 and AW-UE160 public documents describe FreeD output field mappings and Camera ID the same way as the AW-UE150 manual? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  Panasonic's interface specifications for AW-UE150/HE145 (2022), AW-UE100 (2022, producer) and AW-UE160 (2025) list a settable Camera ID command (OSJ:F4) under tracking-data output, while the AW-UE150 operating manual (2025) says the FreeD Type D1 Camera ID field 'Always stores FFh'; the vendor documents conflict on whether Camera ID is configurable. None of the UE100/UE160 documents read gives a field-by-field FreeD mapping.
• How do the original 3DGS PLY layout, Khronos KHR_gaussian_splatting and Niantic SPZ differ in coordinate system, colour (spherical harmonics), activation (scale/opacity) and rights, so that conversions between them are correct? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  The reference 3DGS code (54c035f7) writes PLY columns holding pre-activation parameters (log scale, pre-sigmoid opacity), so copying them into KHR_gaussian_splatting (linear scale, 0..1 opacity, degrees 0-3, required colour space) needs exp/sigmoid conversion; SPZ (MIT) stores RUB coordinates, names PLY as typically RDF and GLB as LUF, and supports SH degree 4, which KHR cannot carry without truncation. The three components carry different terms: 3DGS code research/non-commercial, SPZ MIT, KHR text Khronos copyright with a CC-BY-4.0 header.
• Beyond SFU, ACCAD, CMU and KIT, which further AMASS component datasets state their own licence on public pages, and what do they say? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  Three AMASS-related components state their own terms: HDM05's page (archived 2021, last modified 2015) labels the database CC BY-SA 3.0; BMLmovi licenses its data for non-commercial research only, prohibits training methods or neural networks for commercial use, and says the part included in AMASS falls under the AMASS licence; Dynamic FAUST's MPG licence covers 'Software/Data' for non-commercial research and also prohibits training neural networks for commercial use.
• What does the Wikimedia Commons imageinfo extmetadata return for licence and credit, and how does the extension documentation qualify those fields? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  Wikimedia's CommonsMetadata extension describes its extmetadata fields as a temporary solution that outputs parsed HTML and warns that licence values are unreliable for multi-licensed images (with License a best guess and LicenseShortName probably more reliable); a sampled file (Hopetoun_falls.jpg) reports CC BY-SA 3.0 in the licence fields while its categories include GFDL and 'License migration redundant', i.e. a multi-licence case the single licence field does not show.
• How does an open asset-management system identify an asset, its versions and its files, and how are dependencies recorded? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  At ayon-backend 0a2e5cdd, uniqueness is scoped case-insensitively by parent: folder names under a parent, product names per folder, version numbers per product and representation names per version, with the product/version/representation rules applying only to active rows; the licence is FSL-1.1-ALv2 (source-available, no Competing Use, converting to Apache-2.0 two years after each release), which GitHub metadata reports as NOASSERTION.
• What ExifTool sample files exist for metadata testing and what do the repository and sample-image page say about their reuse? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  At ExifTool 2200871d the README says it is distributed on the same terms as Perl (Artistic License or GPL), while the LICENSE file is the GPL v3 text; the repository ships 194 verification test files under t/images (722,199 bytes) with no file-level licence statement found; the separate sample-image archive replaces main images and strips previews 'to avoid copyright problems' while preserving EXIF/APP segments, without stating a licence.
• Is 'kishotenketsu = plot without conflict' supported by scholarly sources, and what do the sources that name the structure actually describe? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  In the sources read, ki-sho-ten-ketsu is a four-stage pattern whose third stage (ten) brings an abrupt change or new topic: Hinds (as reviewed by Premaratne, 2013) found it in translated Japanese newspaper expository prose and the review calls his study not wholly reliable because of translation, and Nintendo designer Koichi Hayashida describes the four-panel-comic version with a 'change-up' third panel; none of these sources says the structure is plot without conflict.
• I want a ready-made ink or Yarn Spinner story to test a parser: which public ones exist and are they under a clear licence? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  The Intercept's README says The Intercept and ink are released under MIT, but a bundled Freesound sound-pack readme in the same repository marks listed sounds Attribution Noncommercial (CC BY-NC 3.0), so the repository-level MIT sentence does not cover all bundled media.
• Which public OpenUSD test assets exist (usd-wg/assets, Pixar Kitchen Set), and which of them state terms that would let L10 use them? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  The usd-wg/assets repository (3b75c2da) declares licences per asset in each readme (typically CC0 or highly permissive) with the repository licence as fallback, while Pixar's Kitchen Set is offered only under a temporary, revocable licence for personal, non-commercial testing of USD.
• Which licence applies to Netflix Open Content titles in AV1/, av2ctc/ and IMF/, and does it match what the Open Content page says? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  Netflix's Open Content page says its open source content is available under CC BY 4.0, but the per-title licence files for the Chimera AV1 encodes (Sept 2019) and the Meridian IMP/VDM/Atmos assets (Nov 2016) license those sequences under CC BY-NC-ND 4.0, and the AV1 readme says each asset's licence is in its own license.txt; the TechblogAssets Sparks licence file referenced by the README returns 404.
• What do the LRS2 and LRS3 pages and licence file say about permitted use of the data, and do they address model training? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  LRS2 is offered for non-commercial academic research only after signing a BBC R&D Data Sharing agreement (agreement not read); LRS3 is described as available for research purposes under CC BY 4.0 while its licence file says the underlying TED video excerpts must respect TED terms and CC BY-NC-ND 4.0, copyright stays with the video owners, and downloads are no longer offered on the site. None of these texts mention model training.
• What terms do MedleyDB and FMA state for their audio, annotations and metadata, and do they address model training? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  MedleyDB's pages offer the dataset for non-commercial research under Creative Commons (named both as Attribution-NonCommercial and as BY-NC-SA 4.0) and ask users not to republish without consent; the Zenodo audio record (v1.0) is access-restricted with no licence field and points to a GitHub repository for annotations whose LICENSE is MIT, while the description page says audio and annotations are released under BY-NC-SA. FMA separates MIT code, CC BY 4.0 metadata and per-artist audio licences, for research purposes. Neither text addresses model training.
• What do the Common LUT Format, the Adobe .cube specification and OCIO's .cube readers define for LUT size, ordering, domain, bit depth and interpolation? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  ACES CLF v3.0 (aces-docs 7c34c210) requires linear interpolation for LUT1D (at most 65536 entries recommended), defaults LUT3D interpolation to trilinear (tetrahedral optional) and orders LUT3D entries with the third (blue) component fastest, whereas the Adobe Cube LUT Specification 1.0 (Sept 2013) orders red fastest, defines DOMAIN_MIN/MAX (default 0-1), and says table values are set for tetrahedral 3D interpolation. The Cube document's licence sentence names CC Attribution Non-Commercial 3.0 but links the by-nc-sa/3.0 (ShareAlike) URL.
• What is the status of APCA and WCAG 3 contrast relative to WCAG 2.2, what does the WCAG 3 draft actually require, and where do APCA and WCAG 2 differ? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  The WCAG 3.0 Working Draft of 10 September 2026 leaves its text-contrast measure 'to be determined' and does not mention APCA (curator search of the same bytes the producer pinned found no occurrence); apca-w3 (6c5c066c) uses a 2.4 exponent and polarity-specific constants, structurally unlike WCAG 2's symmetric ratio, and both APCA repositories state patents pending and restrict use (apca-w3: WCAG web content via a W3/AGWG agreement; SAPC-APCA: registered beta testers or personal use unless authorised in writing).
• Which AMASS component datasets state their own licence or terms on their own public pages, and how do those statements differ from AMASS's website and repository licence? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  The AMASS website licence treats the AMASS data and software as one Dataset licensed only for non-commercial research, education or artistic projects, while component sources state their own differing terms: SFU says research-only and no commercial products or resale, ACCAD labels its Open Motion Project CC BY 3.0 Unported, and CMU's info page says its motions are free to download and use. The pages read do not say how component terms apply to AMASS's fits of the same captures.
• Which public museum open-access programs release images for reuse, and which parts (data, images) are actually under CC0? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  The Met and NGA open-data READMEs state that image files are not part of their CC0 datasets, while Cleveland states images for up to 30,000 works are offered on the same terms as its dataset; all three ask users not to use museum trademarks or imply endorsement. Dataset-level CC0 therefore does not establish image rights for Met or NGA items.
• Which glTF-Sample-Assets models carry non-CC0/CC-BY terms (non-commercial, EULA, testing-only) that L10 must exclude or handle separately? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  At 15cd02d3 the repository's REUSE.toml has 151 annotation blocks: 62 plain CC0-1.0 and 46 plain CC-BY-4.0 (curator re-tally matches the producer); others combine CC licences with trademark references or name non-open terms (SCEA, CRYENGINE agreement, 3DRT testing-only, Poser EULA, Adobe Stock, CC-BY-NC-SA-4.0, CC-BY-4.0 AND CC-BY-NC-4.0). VirtualCity's 3DRT grant is for testing glTF tools only, and DamagedHelmet lists CC-BY-4.0 and CC-BY-NC-4.0 together without file-level scope.
• What files, metadata and HLS settings does Apple state for authoring and publishing Apple Immersive Video, and where do the stated bitrate tiers disagree? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  Apple describes Apple Immersive Video as captured at 90 fps with more than 50 MP per eye, targeting 60 pixels per degree and up to 230 degrees field of view; WWDC25 session 403 recommends MV-HEVC 4320x4320 per eye at 90 fps in P3-D65-PQ for HLS, with the AIME VenueDescriptor and APAC audio referenced from the playlist. The session's spoken tiers (25-100 Mbps average, 50-150 Mbps peak) conflict with its own summary (25-150 Mbps average); the conflict is preserved.
• What does imagineNATIVE's On-Screen Protocols & Pathways state about consultation, story ownership and community review, and for whom is it written? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  The imagineNATIVE-commissioned guide (dated 25 March 2019, written by Marcia Nickerson) says that permission to share a gifted story can be separate from the intellectual-property rights held by its keeper (family, community or nation), that consultation is needed at the beginning and throughout, that consulting one elder does not give sign-off, and that the protocols are a living document rather than a static checklist; it gives a rough-cut community screening as one example, not a required step.
• Which open-source screenwriting apps (Trelby, Starc, Beat, afterwriting) read and write FDX and Fountain, and what licence does each ship under? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  Trelby 2.4.16.2 licence statements disagree: LICENSE is GPL v2 text, setup.cfg declares GPL-3.0-or-later and debian/copyright says GPL-2 (curator-read pinned bytes); afterwriting v1.17.3 README states MIT. The Trelby conflict is preserved, not resolved.
• What consent, watermark and disclosure mechanisms does VibeVoice document, and are they still enforced in the repository? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  The VibeVoice-1.5B HF card (c00898d2, MIT front matter) documents consent-based out-of-scope uses, an audible disclaimer and an imperceptible watermark; the GitHub README (16fb2cb1) says the TTS code was removed on 2025-09-05 after misuse and marks the 1.5B TTS entry Disabled. Card and README describe different artefacts at different revisions.
• How do storyboards mark camera moves (arrows, zoom lines, labels), and where do sources disagree on move names like truck, track and dolly? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  'Truck' is used for Z-axis motion by Toon Boom Storyboard Pro 24 docs, for lateral motion by the IIT Bombay D'source course (archived 2025-03-18), and for following action generally by Penn State Media Commons; no single usage is shared across these sources.
• DawDreamer docs at e0daff3c state both that automation granularity is the block size and that automation data is interpreted at audio rate; the render loop calls automateParameters once per block with the buffer size, consistent with block-wise application (interpolation code not... active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  DawDreamer docs at e0daff3c state both that automation granularity is the block size and that automation data is interpreted at audio rate; the render loop calls automateParameters once per block with the buffer size, consistent with block-wise application (interpolation code not read).
• What memory thresholds does the RAM-pressure default use, how did they change between the flip commit and v0.23.0, and where do the PR description and code disagree? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  At the flip commit 5aa5ccc9 the default thresholds were active 25% of RAM (4-32 GB) and inactive 75% (12-96 GB). Three days later commit b30e980a (PR #14089, listed in the v0.23.0 notes) lowered them to active 10% (2-10 GB) and inactive 100% (max 96 GB), with the stated reason that many users have 'it just fits' workflows. The PR #13802 description says the second argument defaults to 25%, which contradicts the 75% in the merged code. The same release also reverts the 'disable non-dynamic smart memory' step of #13802 (PR #14183). Net behaviour at v0.23.0 was not read from main.py at the tag.
• For keeping one person's face identity across storyboard panels, what do the PhotoMaker and InstantID papers and official repositories measure, what limits and compute do they state, and how are their code and checkpoints licensed? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  PhotoMaker (arXiv 2312.04461v1; repo 060b4fc) stacks 1-4 ID photos into one embedding for SDXL; its Table 1 reports PhotoMaker CLIP-I 73.6, DINO 51.5, Face Sim. 61.8 at 10 s on a V100 (IPAdapter has higher Face Sim. 67.1), trained on 8 A100 for two weeks; it handles one person per image and is better at half-length portraits. InstantID (arXiv 2401.07519v2; repo 2145b67) uses one face photo with an InsightFace embedding, a ControlNet-style IdentityNet and an image adapter, trained on 48 H800; the paper has no quantitative table (qualitative comparisons) and the README supports only the largest face. Licence components differ: both codebases are Apache-2.0 (PhotoMaker's LICENSE header mentions third-party components but lists none after the Apache text); InstantID's README says InsightFace face models are non-commercial research only and its released checkpoints are research only, while the Hugging Face card says the project is Apache.
• How does ConsiStory keep one subject consistent across prompts without training, how was that measured, what are its stated failure modes and costs, and can the official code be used commercially? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  ConsiStory (arXiv 2402.03286v3, SIGGRAPH 2024 TOG) shares internal activations between the images of a set so that a subject stays consistent without any optimisation step; the first two prompts act as anchors (paper: two anchor images, 0.5 dropout). The authors evaluate 100 image sets with DreamSim (background removed) and CLIP and a 3,000-response two-alternative user study; the quantitative headline is a plot, not text. Timing: 32 s on an H100 for two anchors plus one new image, about 25x faster than The Chosen One (their estimate of 13 min). Stated limits: it relies on cross-attention localisation (failures below 5% in their observation, fixable by changing the seed), images in a set must share one style, and SDXL biases carry over. The official NVlabs code is under the NVIDIA License, which permits only non-commercial use and only with NVIDIA Processors.
• Which of the multi-shot and identity-consistency systems and benchmarks in these papers are actually released, as what (code, weights, data), and under which stated terms? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  Released: HoloCine (14B full and sparse weights as .safetensors on Hugging Face, code, CC BY-NC-SA 4.0), StoryMem (code, Hugging Face weights, S-Lab licence non-commercial; Hugging Face metadata says CC BY-NC 4.0), and OpenS2V-Eval (code Apache-2.0). Partly released: MuSS (data-construction code and YouTube ID lists only). Not found released: EntityBench data/code, EntityMem, PersonaShot, MuSS checkpoints. Both HoloCine and StoryMem require separately downloaded Wan2.x base weights (HoloCine README names .pth files, a pickle-capable format) whose terms were not read here. None of the licences were interpreted for output use.
• What steps, learning rates, class-image counts and VRAM figures do the DreamBooth and textual-inversion papers and the diffusers v0.41.0 docs state, and where do they differ? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  As stated: DreamBooth paper ~1000 iterations, prior-loss weight lambda=1, learning rate 1e-5 (Imagen) or 5e-6 (Stable Diffusion), 3-5 images, ~1000 class samples (fewer possible), about 5 minutes on one A100 for Stable Diffusion. diffusers examples/dreambooth README: 5e-6 with 400 steps (no prior), 5e-6 with 800 steps and 200 class images (prior-preservation), 2e-6 for the 12 GB variant, LoRA DreamBooth 1e-4 and 500 steps, with the text encoder needing at least 24 GB. Textual inversion paper: batch size 4, base lr 0.005 scaled to 0.04, 5,000 steps on 2 V100s, about two hours per concept; diffusers README: 5.0e-04 with --scale_lr and 3000 steps. Hugging Face's own blog experiments report 400 steps at 2e-6 for objects and ~1200 steps at 1e-6 for faces. The values differ by source and model, and are used as stated; none is a universal setting.
• Where do licence statements, dependency notices, dataset provenance and weight file formats disagree or leave gaps for these 3D generators? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  Four items need curator attention: (1) TripoSG advertises MIT but its NOTICE lists code derived from Tencent HunyuanDiT (Tencent Hunyuan Community License notice) and the BRIA RMBG-1.4 background-remover whose card says non-commercial; the README downloads RMBG weights. (2) TRELLIS-500K metadata says MIT while the DATASET.md describes assets curated from Objaverse(XL), ABO, 3D-FUTURE, HSSD and Toys4k and states the dataset is CSV metadata; asset-level licences were not read. (3) Hunyuan3D repos ship .ckpt (pickle-capable) next to safetensors; 2.1 ships .ckpt and .bin; TripoSR ships model.ckpt; the licence texts do not address file formats. (4) The Tencent Hunyuan 2.0 HF card links its licence at LICENSE.txt while the HF file list shows LICENSE.
• Which systems claim to steer a running world model or long video with text, how was that steering actually tested, and what did the tests show? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  Four measured protocols for text steering exist in 2025-2026 preprints, plus one system (Zing-0.5) that shows it only qualitatively, and each measures something different. Hunyuan-GameCraft-2 uses a VLM judge on six interaction dimensions over 100 test images against image-to-video baselines. Incantation uses blinded human ratings (three annotators, 400 clips) of whether an entity performed the prompted action. LongLive uses CLIP score per 10 s segment over 160 videos with six prompts each. WorldSonus compares a mid-stream sound prompt switch against a no-switch hold with identical visuals (audio only). Zing-0.5 measures only navigation (WBench) and shows text events as a qualitative session whose lasting consequences the authors say are not established. No source tests a text event in a released interactive model with persistence over later actions.
• For the audio-capable world models and sync-focused sound tools found here, what do the repositories and model cards actually say about licence and weights per component, and where do they disagree? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  HelixWorld (Noiz AI) is the one audio-visual world model with a published checkpoint: code and the HF card say Apache-2.0, but the repository NOTICE says the LTX-2 code and model assets inside it are governed by the LTX-2 Community License (paid licence for entities with at least US$10M annual revenue; fine-tuned weights count as derivatives), the paper says HelixWorld builds on LTX-2.3, and the Gemma text encoder has its own terms. WorldSonus is CC BY-NC 4.0 with .pt weights (pickle-capable). V-AURA code is MIT but its checkpoint is a tar.gz with no stated weight terms. Kling-Foley publishes a paper and a CC-BY-4.0-labelled benchmark dataset but no code or weights were found.
• What do Fab and Quixel say a buyer of a Fab Standard License or CC-BY asset may do, and what part of the binding text could not be read without a browser? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  The Fab EULA page (Internet Archive snapshot 2026-10-08) shows only a self-described non-binding summary: commercial use and distribution of Projects allowed, stand-alone resale or free redistribution not allowed, no credit to the publisher required. It does not mention AI or machine learning. The binding EULA text is script-rendered and was not captured, so the Standard License's AI-training position is unknown to this batch. Fab documentation separately says the NoAI tag marks assets not to be used for generative-AI data collection and needs the Standard licence.
• What do Freesound's per-sound Creative Commons licences, attribution guidance and AI-training answers say at the access date, and where does Freesound's own summary go beyond or differ from the Creative Commons legal texts? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  Freesound distributes each sound under the licence its uploader chose (CC0, CC BY or CC BY-NC 4.0, plus legacy Sampling+). Its FAQ now answers AI training as "yes as long as individual sounds' Creative Commons licenses are respected" and, as of July 2026, adds uploader-level Gen AI preferences (open-source-only, non-commercial open-source-only, no generative AI, and a voice opt-out) on top of the licence, exposed to API users for filtering and in Data Packs. Freesound labels its CC-to-training reading as its own interpretation (for example CC-BY requires disclosing the training set); the CC legal code text does not mention AI and the CC FAQ says the answer depends.
• The BBC Sound Effects archive says it is free to download: what does the RemArc licence text actually permit (personal, research, education, commercial), what must I do, and what does it say about text and data mining or AI? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  The BBC Sound Effects site is a script-rendered app whose licence text is embedded in its JavaScript bundle (read as text only). That text (the BBC's Content Licence for RemArc) permits non-commercial, personal or research use and formal education use by students and staff, requires a credit, bars sharing such as uploading to social media, and says text and data mining, computer analysis, or developing or training AI need BBC permission and may cost a fee. Commercial use is routed to Pro Sound Effects; metadata is under the Open Government Licence v3.
• For a Sketchfab model, which document governs what I may do (the per-model Creative Commons label, the Standard or Editorial licence, or the Terms of Use), and how do the NoAI and CreatedWithAI labels bear on use in a production or an AI dataset? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  Sketchfab layers three documents: a per-model licence label exposed by the API (seven CC types plus free-st, st, ed), the paid Standard/Editorial licence agreement, and Terms of Use effective 12 August 2026 that bar using NoAI-tagged content in generative-AI datasets and say the licence in force at download governs. Sketchfab's own 2023 blog says the NoAI tag may not bind outside the platform for CC-licensed models. The API objects inspected show no NoAI field, and the licence agreement page text read has no NoAI clause although the blog says Standard-licensed downloads are contractually covered; these gaps are for curation.
• Which of the scene-graph systems have released code, under what stated licence, and what third-party models, keys or data does each need? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  At the observed commits, Hydra (BSD-style LICENSE), ConceptGraphs (MIT) have permissive code licences, while the 3DSceneGraph repository carries a non-commercial research-use software licence and its data sits behind a separate click-through agreement that was not accessed. ConceptGraphs code is MIT but running it needs third-party segmentation and vision-language checkpoints plus an OpenAI API key, whose terms are separate. A permissive code licence does not state anything about weights, data or outputs.
• What do the vendors' terms and help pages say about using user inputs and outputs to train models, by plan or surface, and about restrictions on using outputs to build competing models? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  Training statements vary by surface. OpenAI: consumer content may be used to train with an opt-out; API and business content is not used by default. Google Cloud: will not use Customer Data to train without permission. Adobe: says it does not train on Creative Cloud subscribers' personal content and that partner models do not change that. Midjourney and Ideogram contain no clear 'we train on your content' or 'we do not' sentence in the terms read; Midjourney's privacy policy lists data collected through training its algorithms and grants itself a perpetual licence over inputs and assets; Ideogram's privacy policy lists training the models among uses of information collected. Google Cloud and OpenAI bar using outputs to build similar or competing models, and Midjourney bars using the Services to develop competitive products.
• At the observation dates, do OpenAI, Google Cloud (Imagen), Midjourney, Ideogram and Adobe Firefly say the user owns image outputs and may use them commercially, and does the plan matter? active
  @veyrul-import · 0 replies · evidence source_inspected/not_run/unreviewed · 2026-10-23
  OpenAI (consumer terms and business agreement), Ideogram and Google Cloud state in their terms that the vendor does not claim ownership of outputs (OpenAI and Ideogram also assign any rights they hold; Google says Generated Output is Customer Data and it asserts no ownership). Midjourney says the user owns assets but ties ownership to a Pro or Mega plan for companies above one million USD annual revenue, and its help article words the same rule as needing the plan to use images commercially. Ideogram's help FAQ defers commercial use to its terms, while the terms do not restrict it; its plan matters for privacy of images. Adobe's FAQ permits commercial use of non-beta Firefly output but is silent on ownership in the text read. This candidate records texts, not legal conclusions.

More