Assets and reference collections

Characters, props, locations, maps, look packs, provenance and asset search

• articleHow do the vendors' docs describe mask-based editing and inpainting (mask format, polarity, fidelity), and what do they say the mask does not guarantee?
  Corrected 2026-10-24 - see C3-B977-02; the original statements below are kept for history and are superseded where the correction says so. Mask formats are not interchangeable: OpenAI needs a same-size mask with an alpha channel and calls masking prompt-based (the model may not follow the exact shape); Ideogram uses black for the area to edit and white to keep, with a same-size mask that must contain both; Imagen takes a black-and-white mask or automatic background, foreground or semantic masks with a dilation setting and a sampling-step knob; Midjourney's editor now routes inpainting through the V8.X Edit Model. Ideogram 4.5 states that untouched pixels are copied exactly, the strongest fidelity claim among the pages read.
• articleWhat reference-based tools do vendors document for keeping a character, subject or style consistent across images, what limits do they state, and where do the docs disagree?
  Corrected 2026-10-24 - see C3-B976-03; the original statements below are kept for history and are superseded where the correction says so. Each vendor offers a different reference mechanism: Midjourney style, character and omni references (with a version-drift conflict, since the newest docs say the V8.2 Edit Model replaces omni and character references), Imagen 3 Customization subject and style references with long lists of unintended uses, Ideogram character and style references on 3.0 and reference images on 4.5, OpenAI multi-image edits with a stated consistency limitation, and Adobe composition and style references with a Strength slider. Every vendor that states limits says consistency is imperfect; none gives an acceptance test.
• articleFor a first image request, which size/aspect, count and prompt-rewriting controls do Midjourney, OpenAI, Imagen on Vertex AI, Ideogram and Adobe document, and which defaults change my prompt before generation?
  Corrected 2026-10-24 - see C3-B1034-01; the original statements below are kept for history and are superseded where the correction says so. Corrected 2026-10-24 - see CUR-0644-01; the original statements below are kept for history and are superseded where the correction says so. All four vendors with machine-readable docs publish aspect/size controls, but with different vocabularies: Midjourney --ar, Imagen enumerated ratios (1:1, 3:4, 4:3, 9:16, 16:9), OpenAI free-form WxH within bounds, Ideogram resolution/aspect enums. Three of them document automatic prompt rewriting that is on by default (Imagen enhancePrompt true, Ideogram magic_prompt auto, OpenAI Responses image tool revises the prompt), so the prompt sent is not necessarily the prompt rendered. Midjourney instead exposes two creativity sliders, stylize (default 100, 0-1000) and chaos (default 0, 0-100). Adobe's per-control pages were not read for this candidate (see not_verified).
• articleHow was the multi-player training data in these papers obtained (bots, simulators, game recordings, single-view video), and what does each source imply about generalising to human play and about rights?
  Corrected 2026-10-24 - see C3-B1057-01; the original statements below are kept for history and are superseded where the correction says so. Five data routes appear: scripted Mineflayer bots in Minecraft (Solaris, Gamma-World), publicly available bots in Rocket League (MIRA), a driving simulator (ShareVerse, CARLA), recordings of a co-op game (MultiWorld, It Takes Two, natural play) and of Counter-Strike 2 matches (WorldCast, OpenCS2; whether players were human is not stated in the passages read), and camera-trajectory unrolling of single-view video (MetaWorld). Authors flag bot-only data as a generalisation gap (Solaris, MIRA). Only MIRA states a publisher permission for its gameplay recordings in the text read.
• articleHow long do Gemini and Vertex keep Google-side files and interaction results, and where must a pipeline save outputs?
  Problem. Batch inputs and Google-hosted video URIs have their own lifetimes that bound when a pipeline can read them. Conditions. Gemini API Files API and Omni video URI delivery; Vertex AI Veo interactions and storageUri. Method. Gemini Files: files are deleted automatically after 48 hours, with 20 GB per project and 2 GB per file; batch input files are uploaded through this API. Omni: videos over 4MB are returned as a Google-hosted URI to poll until ACTIVE before download. Vertex: stored and asynchronous interactions are retained up to 7 days; requests can name a Cloud Storage storageUri output location. Save outputs into your own bucket or storage on completion. Failure modes. Re-reading a 48-hour file after expiry. Limitations. The Omni page read does not state the lifetime of the delivery URI. Version and date. Docs read 2026-10-23.
• articleCan I feed licensed Getty or iStock footage into an AI tool to upscale, extend or animate it for a documentary?
  Problem. Documentary editors licence archive or stock and may want to run it through generative or restoration tools. Conditions. Content licensed under the Getty Images EULA or the iStock License Agreement (undated pages, fetched 2026-10-23). Method. Both agreements bar using content, including captions and keywords, for any machine-learning or AI purposes unless explicitly authorised. A narrow exception allows AI use with creative (non-editorial) content solely for internal archiving, searching, indexing or sorting, and for any permitted editing of licensed creative content, but expressly not for training, fine-tuning or other data ingestion of models. 'Training' is defined to include uploading content to a third-party AI tool that acquires rights. Getty's EULA also terminates the rights if a social platform or AI tool uses the content for its own purpose. Failure modes. Uploading a licensed clip to a cloud video-generation service whose terms grant it rights to inputs. Limitation...
• articleWhich aspect ratios and resolution tiers (512px, 1K, 2K, 4K) does the Gemini API image doc list per Nano Banana model, and what is the default for generation versus edits?
  Problem. Choosing aspect_ratio and image_size for a Gemini image model. Conditions. Gemini API response_format {type: image} with aspect_ratio and image_size fields. Method. By default the model matches the output size to the input image, otherwise it makes 1:1 squares; set aspect_ratio and image_size (1K default, 2K, 4K, and 512px on 3.1 Flash Image only) under response_format. The doc has per-model tables of exact pixels. Nano Banana 2.1 and 3.1 Flash Image share 14 ratios including extreme 1:4, 1:8, 4:1 and 8:1 (for example 1:1 is 1024x1024 at 1K, 2048x2048 at 2K, 4096x4096 at 4K; 16:9 is 1376x768 at 1K). 3.1 Pro Image lists 10 ratios (no 1:4, 1:8, 4:1, 8:1), and Gemini 2.5 Flash Image lists the same 10 at a single resolution (1:1 is 1024x1024). Gemini 3.1 Flash Lite Image supports only 1K. Failure modes. Pixel sizes are fixed per ratio, not free-form (unlike OpenAI's custom sizes) so an arbitrary size is not possible; the 2K token count differs by model, not covered here. The do...
• articleWhat output sizes and aspect ratios can I request from OpenAI's image API, and which are only for the newer GPT Image models (arbitrary WIDTHxHEIGHT within limits, 3840 max edge) versus the three fixed sizes?
  Problem. An agent must pick a size string for gpt-image requests without a rejected call. Conditions. Image API generations and edits; model matters. Method. The guide lists three recommended sizes (1024x1024, 1536x1024, 1024x1536) and, for gpt-image-2.5-sunburst and -flare, custom WIDTHxHEIGHT strings: both edges multiples of 16, ratio between 1:3 and 3:1, no edge above 3840, total pixels 655,360 to 8,294,400; above 2560x1440 is labelled experimental. The openapi.yaml schema for both generations and edits states the same arbitrary-resolution rule for gpt-image-2, gpt-image-2.5-sunburst and -flare and their dated snapshots, and keeps a legacy enum of 1024x1024, 1536x1024, 1024x1536, auto (plus 256x256 and 512x512 flagged as retained only for SDK compatibility). The guide's collapsed earlier-model section gives gpt-image-2 popular sizes including 2048x2048, 2048x1152, 3840x2160 and 2160x3840 and the same constraints. Failure modes. Sending a free-form size to older models such as gpt...
• articleWhy do AI-generated meshes often fail print checks, and which Toolbox check maps to each failure?
  Problem. Text-to-3D meshes often arrive unprintable. Conditions. Marching-cubes-like or fused-surface outputs; Method. Inference only: the failure classes map to named checks: holes and flipped faces = Solid; overlapping shells = Intersections; sliver triangles = Degenerate; paper-thin cloth, hair or fingers = Thickness; floating details = Overhang. Run Check All, then Make Manifold, then re-check and scale. Failure modes. Auto-repair on large openings can invent geometry. Limitations. Reasoning not a measured failure rate; no AI mesh was tested; sources document only the checks, not AI origin. Version and date. Blender 3.6 manual, 2025.
• articlePrusaSlicer says it auto-repaired errors: how far can I trust slicer auto-repair on a broken mesh, and what external fixes does Prusa name?
  Problem. A slicer imports a non-manifold STL and reports repair. Conditions. PrusaSlicer or Slic3r. Method. Prusa's KB says automatic repair works to a limited degree and a dedicated service may be needed; it names a Windows 10 'Fix by the Netfabb' route plus free external tools (Aspose, Formware, Meshmixer, 3D Builder). It rates Meshmixer Make solid as almost always working but with resolution loss. The older Slic3r manual says some problems are out of the slicer's reach. Failure modes. Third-party tool availability changes (inference: the Netfabb route may be dead: a reader comment on the page claims so, unverified). Limitations. The KB page is undated; Slic3r manual is predecessor project. Version and date. Pages read at fetch time.
• articleHow thin can a wall be for an FDM print, and does a slicer's thin-wall option rescue AI-mesh details thinner than one perimeter?
  Problem. Generated figures often have fine detail and paper-thin parts. Conditions. FDM with a 0.4 mm nozzle (PrusaSlicer, ~0.45 mm extrusion width). Method. Prusa's table gives approx wall thickness per perimeter count: 1 = 0.45 mm, 2 = 0.9 mm, 3 = 1.35 mm, 4 = 1.8 mm (settings-dependent). The Detect thin walls option merges two paths into one pass. Failure modes. Walls below one perimeter are not printable and are dropped or mis-printed; thin-wall detection does not fix that. Limitations. Values assume the stock nozzle; resin printers have other limits not covered. Inference: scale a whole model down and many features cross this limit, so check thickness after resizing. Version and date. Page undated; MK3S-era numbers.
• articleWhat does the Toolbox's Make Manifold clean-up do, and what does the Blender extension listing say it is for?
  Problem. After checks flag holes or flipped faces, one needs a first-pass fix. Conditions. Same add-on. Method. Clean Up > Make Manifold attempts to fix bad normals, fill holes and remove empty edges and faces; Clean Up > Distorted triangulates distorted faces; the manual suggests Merge > By Distance for degenerate geometry and a Boolean modifier for intersecting cubes. Scale To can fit a model to an exact volume or bounding axis. Failure modes. The manual says 'attempts', so complex AI topology (many holes, internal shells) may stay non-manifold: rerun Solid after the fix. Limitations. No success rate is given; inference: automatic hole-filling can create wrong geometry on big openings, so inspect. Version and date. Blender 3.6 manual (2025-06-23) and extension listing.
• articleWhat does Blender's 3D Print Toolbox check on a mesh before slicing (Solid, Intersections, Degenerate, Distorted, Thickness, Edge Sharp, Overhang), and what does each flag mean?
  Problem. A generated mesh looks fine on screen but a slicer needs a closed (watertight) surface. Conditions. Mesh selected in Blender with the 3D Print Toolbox enabled (bundled add-on in 3.6; listed as a Blender extension later). Method. Open 3D Viewport > Sidebar > 3D-Print, run Check All or single checks; in Edit Mode, clicking a result selects the offending parts. Solid flags non-manifold edges (edges not shared by exactly 2 faces) and bad contiguous edges (a flipped face). Intersections, Degenerate (zero area/length), Distorted (non-flat quads/ngons that triangulate unexpectedly), Thickness (thin faces), Edge Sharp and Overhang are separate checks. Failure modes. Per the manual, some slicers tolerate intersections, so a flag is not always fatal; results are analysis only, not a repair. Limitations. English page read is the 3.6 manual (latest path 404 at fetch); no numeric thresholds were on the page text read; check defaults live in add-on settings not read here. Version and dat...
• articleWhat does the Smithsonian say about how far to trust its CC0 designation and open-access metadata?
  Corrected 2026-10-23 - see C3-B686-06; the original statements below are kept for history and are superseded where the correction says so. The Smithsonian FAQ says its CC0 designation waives only its own copyright interests, so third-party permissions (e.g. people, trademarks) may still be needed and are the user's responsibility; 'no known copyright restriction' reflects best efforts with available information, and items with limitations can carry CC0 metadata without CC0 media.
• articleDoes the Smithsonian FAQ summarised in the earlier finding come from the cited URL, and does the FAQ say it gives no accuracy guarantee?
  Problem. C2-B90-U3-07 attributes FAQ statements to an IA snapshot but cites only the Smithsonian OpenAccess GitHub README lines 5-12, which contain no CC0 or FAQ text (grep for cc0, faq, public domain finds nothing). Conditions. Using the Smithsonian CC0 designation as a rights signal. Method. I fetched the IA snapshot of si.edu/openaccess/faq (20250912113456). It supports the CC0-is-copyright-only point, third-party permission responsibility, the 'no known copyright restriction' best-efforts wording, and CC0 metadata without a media file. It does not support 'gives no accuracy guarantee': the FAQ says the initiative is committed to ensuring the accuracy of its collections and data (a stewardship statement, not a warranty, so the earlier wording is an inference, not a source statement). Failure modes. Quoting the FAQ with the wrong source URL; presenting an inference as the Smithsonian's words. Limitations. Terms of Use page, which the FAQ refers to for disclaimers, was not read. Ve...
• articleWhich OpenVDB version does OpenUSD currently test against, and is it still from the MPL-2.0 era?
  Problem. Candidate M2-03 says OpenUSD's tested OpenVDB, 10.1.0, is from the MPL era. Nature: (e) changed since. Conditions. OpenUSD v26.11.1 or later. Method. At tag v26.11.1 VERSIONS.md lists OpenVDB 12.1.1 and build_usd.py downloads v12.1.1; at v26.08 both said 10.1.0. The candidate itself states the licence changed to Apache-2.0 from v12.0.0, so the licence caveat attached to OpenUSD's pin no longer applies at the newer release (that licence statement was not re-verified here). Limitations. Only the version pin was checked, not the OpenVDB LICENSE files. Version and date. Fetched 2026-10-23.
• articleHow does IIIF Image API 3.0 expose deep-zoom structure (sizes, tiles, scale factors, size limits) and rights, and what changed from 2.1?
  IIIF Image API 3.0 exposes multi-resolution structure in info.json through tiles (tile width/height plus required integer scaleFactors), optional preferred sizes, and limits (maxWidth, maxHeight, maxArea) that also bound ^max requests. Rights are one URI (Creative Commons, RightsStatements.org or a registered extension), replacing 2.1's attribution, license and logo properties. The spec never uses the term 'deep zoom', but the tile pyramid supports that pattern.
• articleWhat do public sources state about MIDI 2.0 (UMP, MIDI-CI) interchange with MIDI 1.0, and what does one open implementation lose when converting MIDI 2.0 messages down?
  Linux's ALSA sequencer converts MIDI 2.0 to MIDI 1.0 by right-shift truncation (32-to-7 bits >>25, 32-to-14 >>18, 16-to-7 >>9). A bank-valid program change becomes bank-select controller messages followed by a program change. Only note on/off, poly pressure, control change, program change, channel pressure and pitch bend are converted; other MIDI 2.0 channel-voice statuses are dropped. Upscaling uses a bit-repeat scheme. This is one implementation's behaviour, read from code.
• articleFor a newcomer: what do LoRA, DreamBooth and textual inversion each change in an image model, how many example images does each need according to its source, and which source actually covers image models?
  Partially verified: the curator re-read none of the cited sources; S10, S11, S12, S13, S14, S15, S16, S17 rest on the producer's pinned reading. Per the sources: textual inversion (Gal et al., arXiv v1) learns one new word embedding and leaves the model's weights frozen, from 'typically 3-5' images; DreamBooth (Ruiz et al., arXiv v2) fine-tunes the diffusion model itself to bind a rare-token identifier plus class noun to a subject from 3-5 images; LoRA (Hu et al., arXiv v2) freezes pre-trained weights and trains small low-rank matrices, but its paper evaluates language models (RoBERTa, DeBERTa, GPT-2, GPT-3), not image generators. Hugging Face diffusers v0.41.0 docs describe all three for Stable Diffusion-family models and provide training scripts, including DreamBooth-with-LoRA. A newcomer should therefore cite the diffusion papers for DreamBooth/textual inversion and treat LoRA-for-diffusion behaviour as documented by diffusers, not by the LoRA paper.
• articleFor each 4D generator, which components (code, weights, datasets, third-party priors, outputs) have stated terms, what do those texts actually address, and where do texts disagree?
  Rights differ by component and no system is cleared by one licence. Code: 4D-fy Apache-2.0, L4GM Apache-2.0 with embedded third-party notices, Consistent4D Apache-2.0, Stability code MIT, DreamGaussian4D MIT plus Inria non-commercial headers in the same repository, MAV3D no code, Diffusion4D no LICENSE file. Weights: L4GM weights repository carries three statements (front matter apache-2.0, body and LICENSE file CC BY-NC-SA 4.0); SV4D 2.0 is under the Stability AI Community Licence with a revenue threshold worded inconsistently between card and licence; 4D-fy fetches third-party priors (Zeroscope metadata cc-by-nc-4.0; MVDream metadata openrail). Data: Objaverse-derived assets with mixed per-object licences; the Diffusion4D dataset carries only a front-matter apache-2.0. No inspected text addresses model training on outputs; output ownership is addressed only in the Stability licence.
• articleI need a tiny 3D file to test a glTF loader: which Khronos sample model should I start with and where do I read its licence?
  At glTF-Sample-Assets 15cd02d3, licences are stated per model directory: Box ('One mesh and one material. Start with this.') is CC-BY-4.0 for model files, Triangle is CC0-1.0 for model files with CC-BY-4.0 metadocumentation, and both exclude logos and trademarks; the repository README defers to each model's README for detailed licence information.
• articleWhat does Nga Aho Whakaari's Working with Maori in Screen Production say about partnership, script consultants, ownership of footage and its limits?
  Nga Aho Whakaari's guide ((c) 2013, sponsored by the NZ Film Commission and NZ On Air) encourages non-Maori companies to involve Maori writers, producers and directors from the outset, strongly recommends Te Reo consultants (with tribal dialect variation), notes that production companies set waiver terms, and records the association's then-unmet call for joint ownership and guardianship of archived Maori footage.
• articleHow does Smithsonian Open Access define which records are CC0, what does its API require, and what could not be read about its licence fields?
  The Smithsonian Open Access FAQ, as archived on 12 Sep 2025, treats CC0 as a per-item designation and says items not designated CC0 need prior written permission for commercial use; metadata access is via a keyed api.data.gov API.
• articleWhat does TRELLIS output for an image-to-3D asset, and what do its README and licence imply for game or film use?
  Problem. Image-to-3D tools produce meshes of unclear production readiness. Conditions. Using Microsoft TRELLIS to make assets from an image. Method. (1) The README says TRELLIS takes text or image prompts and generates 3D assets as radiance fields, 3D Gaussians or meshes; the example code exports a textured GLB via postprocessing_utils.to_glb with a simplify ratio (0.95 in the example) and a texture_size (1024 in the example), and saves Gaussians as PLY. (2) The README does not describe PBR material channels, UV layout quality, topology or rigging readiness; treat the GLB as a baked-texture proxy needing retopology, UV and material work before engine/film use (inference). (3) Licence: models and most code are MIT; the diffoctreerast and modified FlexiCubes submodules may have different licences, so check them before shipping a product. Failure modes. Assuming MIT covers the whole tree. Limitations. No visual inspection of outputs was performed. Training-data licence questions are co...
• articleHow strongly should I set IP-Adapter's image-prompt scale, how do I limit it to style or layout blocks, and what does it do to non-square references?
  Problem. A reference image should steer look or subject without overriding the text prompt or ignoring the rest of the frame. Conditions. Stable Diffusion 1.5 / SDXL pipelines with an IP-Adapter checkpoint (h94/IP-Adapter), via the original repo or diffusers. Method. (1) Image-only prompting: scale=1.0 with an empty or generic text prompt; for image plus text, start near scale=0.5 and move up for more reference fidelity, down for more diversity and text control (README best practice; diffusers: set_ip_adapter_scale(0.5) balances). (2) In diffusers, scale can be a dict keyed by UNet block so the adapter only acts in selected blocks, e.g. {'down': {'block_2': [0.0, 1.0]}, 'up': {'block_0': [0.0, 1.0, 0.0]}} for layout plus style (the InstantStyle pattern); omitted layers default to 0. Style-only activation uses just up block_0. (3) Multiple adapters or reference images take a list of scales, e.g. set_ip_adapter_scale([0.7, 0.3]). (4) CLIP's default processor centre-crops, so pre-crop ...
• articleDoes the Adobe USD glTF plugin still treat UsdPreviewSurface as the main output? No: at commit 6441b97 the plugin README marks UsdPreviewSurface and ASM deprecated, and writes an OpenPBR (MaterialX) network by default alongside UsdPreviewSurface.
  Problem. C2-B14-D2-13 presents the Adobe plugin as importing glTF PBR to UsdPreviewSurface and supporting KHR_materials_* through an intermediate ASM model, without noting the deprecation. Conditions. Adobe USD-Fileformat-plugins main head 6441b97 (2026-07-17), gltf/README.md. Method. The README says writeUsdPreviewSurface defaults to true but is deprecated, writeASM defaults to false and is deprecated (superseded by OpenPBR), and writeOpenPBR defaults to true. For extension-heavy glTF, prefer the OpenPBR/MaterialX output rather than expecting UsdPreviewSurface to carry the extensions. Failure modes. Pipelines built on the ASM-based mapping will see it deprecated; the transmission row in the extension table has no support marker while KHR_materials_variants is marked unsupported. Limitations. Whether OpenPBR carries each extension is not established here. Version/date. Commit 6441b97, still main head on 2026-10-23.
• articleHow does the ambientCG API identify assets, signal releases and file changes, express dimensions and state licence, and how stable is it?
  Partially verified: the curator re-read S19, S20, S27; S21, S22, S23, S24, S25, S26 were not re-read by the curator and rest on the producer's pinned reading. ambientCG states all assets are CC0 1.0 with no credit needed, but its API records carry no licence field (licence comes from the policy page), sampled dimension fields are 0 with no unit defined, and the operator warns the API may not be stable enough for enterprise use; v3 (from 2026-02-28) and repackaging updates change file names.
• articleWhich public test-media sources give a licence statement per file, which only per collection, and which should an L10 experiment avoid unless it checks the individual file?
  By texts read: Wikimedia Commons requires a licence tag on every file description page but disclaims any warranty, so the page revision and tag are the evidence; Khronos glTF-Sample-Assets keeps licence and metadata per model directory (cycle-2 C2-B70-W2, not reread); Blender open-movie sites state CC BY 3.0 per project, not per file (cycle-2 C2-B71-W3-01); Freesound's API documents a licence field per sound (CC0, Attribution, Attribution NonCommercial) plus a generative-AI-preference field, which I did not call; Xiph's test media pages are collection-level ('believed to be freely redistributable') with per-clip notices that include research-only terms, so they are not unambiguous per file. Netflix open content copies are held as conflicting by curation (CA-RC-NFX).
• articleWhich training datasets does each of Real-ESRGAN, FILM, RIFE and Practical-RIFE itself name, and where is that stated?
  Real-ESRGAN names DIV2K, Flickr2K and OutdoorSceneTraining (OST) in its paper and DF2K plus OST in docs/Training.md. FILM names Vimeo-90K as its main training dataset (README) and as training data (paper). RIFE names Vimeo90K in its paper and README. The Practical-RIFE README at the pinned commit names no training dataset, so its data lineage is unknown from that file. REDS is not named in the four model repositories read.
• articleHow do COLMAP, Meshroom, Metashape and RealityScan establish real-world scale and units for a photogrammetry result?
  Partially verified: the curator re-read S15, S19; S24, S25, S26 were not re-read by the curator and rest on the producer's pinned reading. Reconstructions have no inherent real-world scale: COLMAP geo-registers by fitting a similarity transform to known camera-centre positions, and Meshroom's SfMTransform can scale to real-world size (its auto_from_landmarks mode only fits landmarks into a [-1,1] box, i.e. normalises rather than measures). RealityScan's one-distance rule and Metashape's markers/scale bars are producer-read only.
• articleWhat capture rules do COLMAP, Meshroom and Agisoft Metashape state for photos used to build a 3D asset, and where do their numbers differ?
  Partially verified: the curator re-read S14, S18; S15, S22, S24 were not re-read by the curator and rest on the producer's pinned reading. COLMAP asks for high visual overlap with each object seen in at least 3 images; Meshroom asks for 60% side and 80% frontal overlap, no flash, fixed focal length and no shadows, reflections or transparent objects. Metashape's overlap figures (60/80% aerial; 60-70% close range) and its no-crop/rotate rule are producer-read only.
• articleWhat files and 3D-asset outputs (point cloud, mesh, UVs, textures, formats) do COLMAP, Meshroom and Metashape state they produce?
  Partially verified: the curator re-read S14, S15, S20, S21; S16, S24 were not re-read by the curator and rest on the producer's pinned reading. COLMAP's automatic reconstruction writes a fused.ply dense cloud and Poisson and Delaunay PLY meshes, with texturing as a separate mesh_texturer step producing an atlas with per-face UVs; Meshroom's Texturing writes texturedMesh.obj/.mtl and texture_*.png, prefers Alembic for point-cloud interchange and has FBX support paused. Metashape's export list is producer-read only.
• articleWhat identification fields and filename rules does the ETC/MovieLabs VFX Image Sequence Naming specification define, and how does it treat versions versus revisions?
  The curator re-read all cited web sources (S29); nothing was executed. The ETC VFX image-sequence naming report v1.0 (2020) defines identification objects (show, VFX sequence, 4-digit VFX shot, image type with instance number, description, vendor and revision codes, alternate, multi-camera reference, frame number) composed into a file name with fixed separators kept even when a parameter is missing, consistent case (lower case preferred) and names independent of directory paths. Literal token spellings were lost in PDF text extraction.
• articleWhen a REUSE.toml annotation covers a file that has its own header, are copyright and licence decided together?
  Problem. C2-B20-H3-08 says with precedence 'closest' file headers or sidecars win and the table is only a fallback. Correction (missing limitation). The spec says the closest algorithm is applied separately for copyright and for licensing, so a file with a licence header but no copyright header can still take its copyright from the annotations table, and vice versa. Conditions. REUSE spec 3.3, annotations tables with default precedence. Limitations. Behaviour of the reuse tool itself was not tested. Version/date. Spec 3.3, 2024-11-14.
• articleHow machine-readable is per-asset licence and credit metadata in the Poly Haven API, the Sketchfab Data API, OpenGameArt pages and Kenney pages, and what must an importer parse out of free text?
  Poly Haven's API gives per-asset authors and descriptions but no licence field (CC0 is stated site-wide; only 3 of 521 model descriptions mention it), so an agent must take the licence from site terms. Sketchfab exposes a structured licence object on model detail, but unfiltered search results for non-downloadable models carry a null licence, so licence presence depends on downloadability and endpoint. Author credit is a structured field only on these two services among those surveyed.
• articleWhat does MusicXML 4.0 define for notated versus sounding (MIDI-compatible) data, and what do its own version notes say changed for MIDI tooling and file structure?
  Partially verified: the curator re-read S2, S5; S1, S3, S4, S6 were not re-read by the curator and rest on the producer's pinned reading. MusicXML's own tutorial splits the format into notation (display/print) elements and sounding elements that support MIDI playback, of which only the sounding elements are required; durations follow MIDI as divisions per quarter note; version 4.0 removed the midixml DTD/XSL without XSD replacements. No MusicXML text read enumerates conversion losses.
• articleHow do Recraft's style references and style_id work for keeping a set of images on-brand (1-10 references, flexible vs precise match), and what are the rules?
  Problem. Producing many images that share one visual identity. Conditions. Recraft API V2/V3/V4/V4.1 (not V4.1 Flash), docs 23 Oct 2026. Method (documented). A custom style is built from one to ten reference images (PNG, JPG, WEBP; 64 MB total, each file under 20 MB) with no training; references can come from other generators, branding materials or existing assets. Use it by style_id (create once with Create style) or by attaching style_references / style_reference_urls to a generation, which creates a private style and returns its style_id for reuse; sending both is rejected. V4 and V4.1 styles have a match value: flexible (default) matches the general vibe, precise follows the style meticulously, including rendering technique, colour, composition and lighting; style_match in a request overrides the stored value. The dedicated V4 Styles models always require a style. Guidance: a single reference is enough to start; similar images sharpen the match and diverse ones widen the range. ...
• articleWhat do OpenAI and Google docs say about keeping characters and brand elements consistent across generations, and how many reference images can I give?
  Problem. Logos, mascots and products must repeat accurately across images. Conditions. OpenAI GPT Image docs and Gemini (Nano Banana) docs, 23 Oct 2026. Method (documented). OpenAI lists consistency as a limitation: the model may occasionally struggle to keep recurring characters or brand elements consistent across multiple generations; it also lists composition control (difficulty placing elements precisely in structured or layout-sensitive compositions). Google's model summary describes the premium Gemini 3 Pro Image model as offering accurate brand consistency and its Nano Banana 2.1 as improving multi-turn consistency (vendor claims); the Gemini reference table gives up to 4 or 5 character images for character consistency depending on the model. Use [inference]: treat logos as assets, not generations: place the real logo file (vector or high-res PNG) in the composite after generation; use the model for backgrounds and scenes; if a mascot must recur, use the vendor's reference-im...
• articleWhat rights and attribution metadata does IIIF Presentation carry and how do rights, requiredStatement, provider and metadata differ?
  IIIF Presentation 3.0 splits rights information three ways: 'rights' holds one Creative Commons or RightsStatements.org URI (or a registered extension) and is informative and machine-oriented, possibly shown only as an icon; 'requiredStatement' holds label/value text that must be displayed when the resource is displayed or used; 'provider' gives structured data about who supplied the content. Institution-specific wording therefore goes in requiredStatement or metadata, and a manifest without 'rights' asserts nothing about status. Presentation 2.1 used 'license' (URI) and 'attribution' (text that must be shown) for the same split.
• articleWhich open image-to-3D and text-to-3D asset generators have released code and weights, and what file or representation does each one produce?
  Corrected 2026-10-23 - see C3-B588-04; the original statements below are kept for history and are superseded where the correction says so. Eight open releases were read at pinned commits. Only Microsoft TRELLIS (text-base/large/xlarge) ships text-conditioned weights, and its README itself says to prefer text-to-image followed by TRELLIS-image. TRELLIS emits Gaussians, radiance fields and meshes (GLB/PLY export in the README example); TRELLIS.2 emits a mesh with PBR maps (GLB); Hunyuan3D 2.x emits a trimesh shape then a separate texturing stage (2.1 adds PBR); SF3D and SPAR3D emit UV-unwrapped GLB with material parameters; TripoSR emits a mesh (vertex colours or optional baked texture); TripoSG emits an untextured shape (GLB). Hardware floors stated by the vendors range from about 6 GB to 24 GB of GPU memory.
• articleWhat do primary sources say, measured or claimed, about topology, UVs, polygon budgets and PBR correctness of generated assets for games, previs or VFX?
  Corrected 2026-10-23 - see C3-B588-05; the original statements below are kept for history and are superseded where the correction says so. No inspected source measures retopology quality (edge flow), UV distortion or engine polygon-budget compliance, and none tests PBR values against ground-truth materials of a held-out asset. What exists: SF3D reports triangle counts for one mesh per method (SF3D 27.4K vs TripoSR 32.1K, OpenLRM 662K) and a box-projection UV unwrap in 0.5 s, with remesher options (triangle, quad split to triangles); TRELLIS.2 reports PSNR/LPIPS on rendered PBR maps for reconstruction, offers GLB export with remesh and a decimation target (README example 1,000,000 faces, 4096 texture), and states small holes occur; SF3D and SPAR3D state material estimation is homogeneous or sometimes suboptimal; TRELLIS (first release) states baked-in lighting and no PBR; Hunyuan 2.0 describes a low-polygon stylization module in its hosted Studio. Production claims are the vendors'.
• articlePer component (tokens, raw video, weights, code) do the 1X cards, the GitHub README/LICENSE and the 1X blog agree on terms, and which uses does each text actually address?
  Corrected 2026-10-23 - see C3-B588-08; the original statements below are kept for history and are superseded where the correction says so. For each component every text read gives the same label: tokenised data Apache 2.0 (HF card, GitHub README schema block, 1X blog), raw video CC-BY-NC-SA 4.0 (raw card front matter, tokenised card prose, 1X blog), GENIE weights apache-2.0 (card front matter/API), code Apache-2.0 (LICENSE text). Different labels on different components are not a conflict. No text addresses hosting, redistribution, modification, training, commercial or output use except by the label itself; stated uses are purposes (experimenting with robotics data, challenge participation) and a contest rule. No rights conflict is filed.
• articleWhere are the TRELLIS.2 small-hole limitation and the SF3D, SPAR3D and TRELLIS v1 material or baked-lighting statements actually stated?
  Correction (unsupported by the cited source). C3-B080-W16-07 attributes several limits to the cited READMEs: TRELLIS.2 'states small holes occur', TRELLIS first release 'states baked-in lighting and no PBR', and SF3D/SPAR3D 'state material estimation is homogeneous or sometimes suboptimal', plus SF3D triangle counts and a 0.5 s UV unwrap. In the pinned READMEs fetched 2026-10-23 none of these statements appears. The TRELLIS.2 small-holes statement is real but sits in the Hugging Face model card, under Known Limitations. The SF3D/SPAR3D and TRELLIS v1 statements and the SF3D numbers were not found at the cited sources (they may be in papers or HF cards not cited). Cite the card for the holes statement and treat the rest as unverified until a source is added. Version/date. Fetched 2026-10-23.
• articlestempeg (a41eaabb) code is MIT while its bundled example stem (The Easton Ellises excerpt) is CC BY-NC-SA 3.0 per README; the media component therefore carries non-commercial and share-alike conditions distinct from the...
  stempeg (a41eaabb) code is MIT while its bundled example stem (The Easton Ellises excerpt) is CC BY-NC-SA 3.0 per README; the media component therefore carries non-commercial and share-alike conditions distinct from the code.
• articleHow does Europeana's own rights-statement set relate to RightsStatements.org, and what should an agent expect to see in Europeana records?
  Europeana accepts 14 rights values: Creative Commons licences and tools plus six RightsStatements.org statements (InC, InC-EDU, InC-OW-EU, NoC-NC, NoC-OKLR, CNE); InC-RUU, NoC-US, NoC-CR, UND and NKC are not in its list. It states rights statements are not licences, discourages CNE (the RS vocabulary itself describes CNE neutrally) and requires providers' best efforts, warning that a wrong public-domain label misleads users. RS JSON-LD closeMatch links point at legacy Europeana rights URIs (InC to europeana.eu/rights/rr-f/, CNE to /rights/unknown/, InC-OW-EU to /rights/orphan-work-eu/; InC-NC to CC BY-NC 4.0), so legacy and RS URIs may both appear in older data.
• articleHow does an agent read a RightsStatements.org URI as data, and which machine-readable properties does each statement actually carry?
  Each of the 12 RightsStatements.org 1.0 URIs returns JSON-LD under content negotiation (all dated 2022-04-27, version 1.0). The machine layer is thin: closeMatch links on 4 statements, relatedMatch on 10, and a CommercialUse prohibition only on InC-NC and NoC-NC; InC-EDU's educational permission exists only in prose (an ODRL prefix is declared but unused). The technical white paper says URIs are opaque to machines and requires HTML5+RDFa, JSON-LD and Turtle representations. So software can classify a status but cannot read most permissions from the data.
• articleWhere do the declared 1.0 meta fields (and the 0.x to 1.0 migration output) and the VRM Public License text read differently?
  VRM 1.0's meta.md defines commercialUsage values personalNonProfit (default), personalProfit and corporation, but the English VRM Public License 1.0 text uses only 'Non-commercial' and 'personal use' wording (no 'corporation' or 'personal profit'); UniVRM (efd20f62) migrates VRM 0.x commercial 'Allow' to personalProfit, never to corporation, writes the Japanese licence URL on export, and defines an English URL constant that returned 404.
• articleHow does the Universal Category System define CatID and filenames, which version is published, and how do tools carry UCS data in BWF/iXML?
  The UCS site describes UCS as a public-domain initiative and announces version 8.2.1 (January 2024), whose only CatID change corrects WOOD-HANDLE to WOODHndl; the MIT-licensed third-party ucsrename tool (9fa45437) embeds the v8.2 list with 'WOODHandl', builds filenames as CatID_FXName_CreatorID_SourceID_UserData.Extension and rejects underscores in field values. The filename rules come from the tool, not a UCS specification text.
• articleHow do S3 versioning and Object Lock compare with Cloudflare R2 bucket locks for making generated assets immutable, and what is missing on R2?
  Problem. Making finished renders and their sidecars tamper-resistant for provenance or rights disputes. Conditions. Amazon S3 User Guide (Versioning, Object Lock) and Cloudflare R2 docs (bucket locks updated Oct 20, 2026; S3 API page Oct 14, 2026). Method. S3 versioning is off by default; once enabled an overwrite creates a new version and a delete inserts a delete marker, so earlier versions are recoverable. Object Lock works only in buckets with versioning enabled; in compliance mode a protected object version cannot be overwritten or deleted by any user including the root user and retention cannot be shortened, while governance mode allows privileged bypass (docs describe both). Lock-protected objects also disallow annotation changes; to annotate, create a new version. R2's S3 compatibility table marks GetBucketVersioning and PutBucketVersioning as not implemented; instead R2 bucket locks prevent deletion and overwriting for a period or indefinitely via per-prefix rules (an examp...
• articleHow do I store generated media under content-addressed (sha256) keys without overwriting or racing, using S3 or R2 conditional writes and checksums?
  Problem. Deduplicating and verifying generated assets across retries (see Celery at-least-once finding). Conditions. Amazon S3 User Guide (conditional writes, checking object integrity) and Cloudflare R2 S3-compatibility docs (page updated Oct 14, 2026). Method. Name the object key after the content hash (for example outputs/sha256/ab/abcd...); upload with If-None-Match: * so the write succeeds only if the key does not exist (S3: header prevents overwrites by validating no object with that key; requires SigV4). R2 documents that conditional headers on PutObject are evaluated atomically at commit, and that with concurrent If-None-Match: * on an absent key at most one write succeeds and the others get 412 PreconditionFailed; treat 412 as 'already stored'. S3 can verify uploads with checksums; supported algorithms include SHA-256 (CRC64NVME is the default algorithm for S3 checksum calculation), so send the SHA-256 you computed and let the service reject corrupt uploads (S3-specific; th...

More