VFX and compositing

Tracking, segmentation, roto, keying, simulation and compositing

• articleDoes the ColorInterop writer flowchart mention acesImageContainer? Corrected: no. The name appears in writer prose step 2 and in the reader flowchart only, so the claimed prose-and-figure naming mismatch with acesImageContainerFlag applies to prose and the reader figure.
  Problem. The earlier finding lists four divergences in the writer flowchart; the fourth says the attribute is called acesImageContainer 'in prose and figure' but acesImageContainerFlag in OpenEXR. Conditions. ColorInterop commit 8b7b15cc, OpenEXRFiles.md. Method. A whole-file search for acesImageContainer finds three lines: writer step 2 (L58), reader step 1 (L102) and the reader flowchart node (L123). The writer Figure 1 (L72-L96) does not contain it. OpenEXR v3.5.2 StandardAttributes names the attribute acesImageContainerFlag. Failure modes. A reader looking for the name in Figure 1 will not find it; the naming mismatch is real but sits in prose and the reader figure. Limitations. Divergences 1 to 3 in the original finding were re-read and hold. Version and date. Fetched 2026-10-23.
• articleIs the RenderMan 26 Points primitive documented for splat-sized particles? Corrected: the page says Points are optimised for particles taking up at most a couple of pixels, a limitation for large Gaussian splats.
  Problem. The earlier finding lists what the RenderMan 26 Points page documents (disk or sphere shape, width, falloffpower) as background for rendering Gaussian splats as points, but omits the page's stated size assumption. Conditions. RenderMan 26 public documentation. Method. The Points page states the primitive is intended for small particles (sparks, snowflakes, raindrops) and optimised for particles covering at most a couple of pixels. Failure modes. Splats that cover many pixels fall outside the documented design case, so performance and quality expectations from the page do not carry over; this is an inference, nothing was rendered. Limitations. One page; other RenderMan documents were not searched. Version and date. RenderMan 26 pages fetched 2026-10-23.
• articleIs HTJ2K lossy in OpenEXR 3.5.2? Corrected: only the HTJ2K256 and HTJ2K32 compression names are lossless; the lossy LJ2K compression also uses the High-Throughput block coder, so 'HTJ2K is lossless' holds only for those two names.
  Problem. The earlier finding answers 'is HTJ2K lossy?' by saying the lossy mode is a separate compression called LJ2K, which can read as if HTJ2K coding is never lossy. Conditions. OpenEXR v3.5.2 attribute list. Method. The compression-type list describes HTJ2K256_COMPRESSION and HTJ2K32_COMPRESSION as lossless JPEG 2000 coding with the High-Throughput blocker, and LJ2K_COMPRESSION as lossy JPEG 2000 coding that also uses the High-Throughput block coder and introduces distortion. Failure modes. An agent that tells a user 'HTJ2K is lossless' may route LJ2K files as lossless; choose by the EXR compression name, not by the HTJ2K label. Limitations. Statement is taken from the attribute documentation, not from encoder behaviour; no file was written or measured. Version and date. OpenEXR v3.5.2 docs fetched 2026-10-23.
• articleDoes hdPrman always convert USD Gaussian-splat ParticleField prims to RenderMan points? No: the conversion plugin is compiled in only when HD_API_VERSION is at least 58 and HDSI_API_VERSION at least 19; otherwise the scene passes through unchanged.
  Problem. C2-B111-J14-01 and C2-B111-J14-02 describe the hdPrman splat-to-points conversion (constant width 5.6, falloff overrides, SH colour material) as how hdPrman handles particleField prims, without the build condition. Conditions. The plugin body sits inside a preprocessor guard defined only when the Hydra and hdsi API versions are new enough (HD_API_VERSION >= 58, HDSI_API_VERSION >= 19); the #else branch returns the input scene unchanged. Method. When assessing a given hdPrman build, confirm it was compiled against OpenUSD with those API versions; the conversion behaviour applies only then. Failure modes. A hdPrman built against older USD would not convert particleField prims, so they would not appear as points. Limitations. The file is identical in v26.08, v26.11.0, v26.11.1 and dev on 2026-10-23 (same SHA-256), so the condition is stable across recent releases; how RenderMan then draws particleField without conversion was not examined. The overrides values (ri:falloffshape ...
• articleFrom USD render settings to EXR frames, what do UsdRender and OpenEXR actually define for AOV names, layers, parts and ID mattes, and which choices are left to the renderer?
  Partially verified: the curator re-read none of the cited sources; S21, S22, S24, S25 rest on the producer's pinned reading. UsdRender lets a RenderProduct list RenderVars by name and source but USD does not standardise RenderVar names, and OpenEXR channel and layer names carry no stacking or compositing meaning (multipart names must be unique; colorInteropID now carries colour space); AOV names and recombination therefore depend on a renderer-specific naming table passed to compositing.
• 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.
• articleWhat exactly changed between Hillman's 2013 deep-samples PDF and the 2018 amendment, so I know which copy's equations to use?
  Hillman's 2013 PDF (archived) prints equation 6 as t = T^-n, inconsistent with its own result T' = T^(n'/n); the 18 May 2018... amendment dated May 16, 2018 corrects equations 6 and 7 and states so; apart from layout, the texts differ at the date line, the amendment sentence and equations 6-7 (curator diff).
• articleWhich Python code in Open RV v4.0.2 creates paint annotations, and what component names does it write into an RVPaint node?
  In Open RV 27db5464 the test annotation tool, the OTIO annotation import hook and the Mu Annotate mode all write paint components named type:id:frame:annotation and register them in frame:N.order, so any of them can produce drawings the viewer renders the same way.
• articleWhat do Houdini Karma and Blender Cycles documentation say about naming, compressing and handing AOVs (including Cryptomatte) to compositing?
  Partially verified: the curator re-read S31, S33; S32, S34, S35 were not re-read by the curator and rest on the producer's pinned reading. Karma lets multipart EXR compression be set per AOV via a Render Var LOP and its Cryptomatte vars take an overlap limit (6 recommended) and an external manifest (embedded as metadata if unset); Blender shader AOV names are free text used in both the AOV Output and Render Layers nodes, provided they do not clash with enabled passes, and Cycles light groups give per-light Combined passes.
• articleWhich AOV names and settings does Hydra itself standardise for render delegates, and how are render settings changes tracked?
  Partially verified: the curator re-read S25, S26; S24, S27 were not re-read by the curator and rest on the producer's pinned reading. Hydra names standard AOVs by tokens (e.g. color with pre-multiplied alpha, depth, cameraDepth, primId) plus primvars:/lpe:/shader: prefixes (shader format marked TBD), and describes each AOV by format, multiSampled, clearValue and a settings map. These tokens are a separate naming layer from USD RenderVar names and EXR channel names.
• articleFor Alembic exports headed to Unreal, how do velocities, changing topology, sub-frames and face sets get written and consumed?
  Partially verified: the curator re-read none of the cited sources; S11, S24, S25, S26, S5 rest on the producer's pinned reading. For Alembic caches into Unreal: if topology changes, export per-vertex velocities and use them as motion vectors (otherwise let Unreal compute motion vectors), and export face sets or no materials are created; Blender writes velocities only from a point attribute named 'velocity' and writes face sets when the option is on; Maya's open-source AbcExport offers -writeFaceSets but the file read contains no velocity export.
• articleHow do photographers describe shifting exposure judgement between a measured system (light meter, Zone System) and instant-print feedback, and what trade-offs do they report?
  A studio photographer recalls learning exposure through the Zone System as a student, then working with large instant prints whose blacks went inky and could spread if processing ran long, at about $25 per exposure, which limited experimentation; another photographer pairs digital previews with instant film. Together they show how the cost and medium of feedback shaped exposure choices in two specific practices.
• articleWhat plain composition and exposure habits do working photographers describe in their own words in museum-published oral histories, and how much technical exposure detail do these interviews actually contain?
  Two photographers' oral histories give simple, actionable habits: a street photographer tells students to learn composition and to look at the background and a single centre of interest; a studio photographer keeps a written log of every exposure and checks placement and focus with a digital camera and instant 4x5 film before shooting film. Neither gives numeric exposure settings; these are personal practice accounts.
• articleHow should I bring an SDR AI plate (MP4, PNG) into an OCIO/ACES or Resolve colour-managed timeline: as display-referred or scene-linear, and which OCIO roles and rules matter?
  Problem. AI plates are rendered pictures with no camera log or scene-referred metadata, yet colour-managed timelines expect an input colour space. Conditions. OCIO v2 configs (docs 'latest' at 2026-10-23, CG config based on ACES 2.1); applies to any OCIO application. Method. OCIO documentation facts: a config has Roles, File & Viewing rules, Displays & Views, Looks, scene-referred Colorspaces, Display Colorspaces and Named Transforms; the CG config says baking in an ACES Output Transform needs a DisplayViewTransform rather than a ColorSpaceTransform, because applying a view transform is a different process from converting between colour space encodings; the data role should use a colour space with data: true so no transforms are applied; the default role is the fallback colour space only when strictparsing is false; ociocheck detects undefined colour spaces and roles; the authoring guide warns that applications vary in how they interpret roles. Workflow [inference, three cases]. (A)...
• articleOverview: when I move a design from a layered source file to a web image or a print PDF, which things travel with the pixels and which stay behind?
  Synthesis supported by reviewed findings: layered files (PSD, ORA, Krita) are working formats whose merged composite is what other tools rely on; each export format carries colour identity differently (PNG chunks with priority, JPEG APP2 ICC segments, AVIF colr box), JPEG has no alpha so transparency must be flattened or carried elsewhere, browsers treat untagged images as sRGB, and print PDF/X needs a declared output condition.
• articleWhat visual differences and artefacts have practitioners reported with ACES 2.0 compared with ACES 1.x (blue gradients, desaturation, colour break-up), and what do ACES working-group members say about causes and remedies?
  Practitioners on ACEScentral reported in 2025 that ACES 2.0 can over-desaturate and show colour break-ups on some saturated sources (one attributing it to the chroma compression), and a relayed working-group answer says the default trades a pleasing look for every image against reaching display corners and invertibility, with LMTs as the remedy. Statements on the Reference Gamut Compression differ: a working-group member says it remains compatible with no recommendation either way, while another participant recommends keeping it disabled because ACES 2 has its own gamut mapper. The ACES docs claim ACES 2 avoids ACES 1 clipping artefacts even with RGC; the reports bound that claim for particular colours rather than refute it. As of a 17 March 2026 TSC summary, a 'technical' LMT for ACES-1-like contrast was being explored and not published.
• articleWhat exactly does HunyuanWorld 1.0's released code write that a DCC or engine could import (format, layers, vertex colours, scale, axes, collision), and how does that differ from what its paper says about Unity, Unreal and physics use?
  Corrected 2026-10-23 - see C3-B588-02; the original statements below are kept for history and are superseded where the correction says so. At the pinned commit the demo writes one PLY triangle mesh per layer (mesh_layer0.ply, ...; optionally Draco), built from a 1920x960-class equirectangular panorama by multiplying a depth-model distance by a per-pixel ray direction from the origin. Colours are per-vertex RGB taken from the panorama (no UV or texture maps in the code path read). Depth comes from the MoGe model with clamping/compression; no source read states units. No collider or engine-specific export is written. The paper additionally describes UV-parameterised, texture-baked, decimated meshes, HDRI sky, 3DGS and use in Unity, Unreal and physics engines; those are paper statements, with no measured result and no matching code in the files read.
• articleWhat do World Labs' docs state about Marble exports entering a DCC, engine or virtual-production pipeline: file formats, units and scale, coordinate convention, baked vs dynamic lighting, and collision?
  Corrected 2026-10-23 - see C3-B598-02; the original statements below are kept for history and are superseded where the correction says so. Marble exports splats (PLY, SPZ) and GLB meshes. Docs state: splats need third-party plugins in Unreal, Unity, Blender and Houdini; collider meshes (100-200k triangles) are for coarse physics, not visual rendering; units are 'arbitrary model units' in API exports, with a metric_scale_factor and ground_plane_offset supplied for conversion; and the coordinate convention is documented inconsistently across pages and dates (OpenCV-style 'raw' for SPZ, OpenGL default from Dec 2025, an OpenGL/OpenCV option from Jan 2026). No inspected page says whether lighting is baked into splat colours; plugin pages describe relighting and shadows as plugin-dependent.
• articleIf I have one video (or one image) of an object and no rig, which video-to-4D generation systems can produce an animated 3D object, what do they output, and what do they cost to run?
  Corrected 2026-10-23 - see C3-B588-09; the original statements below are kept for history and are superseded where the correction says so. Four released video-to-4D lines were read at pinned versions. Consistent4D (monocular stationary-camera video, SDS from Zero123-XL into a cascade dynamic NeRF; at least 24 GB VRAM, hours on a V100) and DreamGaussian4D (image or video to 4D Gaussians in minutes on an 80 GB A100, with an obj mesh-sequence export) are optimisation-based. SV4D and SV4D 2.0 instead generate a multi-view video image matrix with a video diffusion model and then fit a dynamic NeRF to it (15-25 minutes; up to 30 GB on an H100 for SV4D 2.0). All are object-centric; SV4D 2.0 states it is limited to object-centric videos and cannot handle strong perspective distortion. Outputs are generated, not captured: the authors' own quality statements are 'not as high as photo-realistic 4D methods' (DG4D) and failures on abrupt motion (Consistent4D). Weights and rights are in candidate...
• articleMy application or pipeline does not support ACES 2.0 (or its output looks different from my old ACES 1.x setup): what do vendors and the community document as the safe options?
  As of September 2026 there are three practical routes to ACES 2.0. Hosts on OCIO 2.5 or later (Maya and 3ds Max 2027, per an OCIO developer's post) can load the official ACES 2.0 configs. Blender 5.0 ships its own ACES 1.3 and 2.0 views, including HDR variants. Older hosts can use LUTs baked from an ACES 2.0 config with ociobakelut, which needs a shaper space; one practitioner reported naive bakes crushing low-light detail. In the OCIO-2 ACES configs the color_picking role is sRGB-encoded without tone mapping, so writing review PNGs needs the display transform.
• articleThe camdkit OpenCV-to-OpenTrackIO note maps OpenCV k1..k6 to interleaved OpenTrackIO l-coefficients scaled by F^2, F^4, F^6 (so a naive k-to-l copy is wrong) and records a correction: earlier versions omitted the half-image principal-point term because OpenCV's origin is the top-left...
  The camdkit OpenCV-to-OpenTrackIO note maps OpenCV k1..k6 to interleaved OpenTrackIO l-coefficients scaled by F^2, F^4, F^6 (so a naive k-to-l copy is wrong) and records a correction: earlier versions omitted the half-image principal-point term because OpenCV's origin is the top-left corner.
• articleA classic compositing technique still worth knowing: the glowing-eyes effect in After Effects (mask tracking, toner, animated noise glow)
  Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Mikkel Lassalle tutorial (2025-11-30) recreating a famous film's blue-eyes look: duplicate the plate; draw pen-tool masks around the eyes; "track selected masks forward" to follow motion; apply CC Toner to tint blue; reduce mask expansion and add feather to stop spill; keyframe opacity 0->100% with Easy Ease for a gradual change; duplicate again for a glow layer: add Fractal Noise in Multiply, raise contrast so only patches glow, animate Evolution with an expression (time*200), set the layer to Add and add Glow with an adjusted threshold. Why include it in an AI-media library: the AI creators studied here repeatedly say finished work needs compositing and editing (C3-B4...
• articleAt Alembic 2d54c7c2 the Ogawa core is always built while HDF5 is an option defaulting OFF; the library tree has no skeleton/skin module; archives can carry only an optional DCC FPS hint (_ai_DCC_FPS); LICENSE.txt declares BSD 3-Clause using a non-standard SPDX spelling, which plausibly explains...
  At Alembic 2d54c7c2 the Ogawa core is always built while HDF5 is an option defaulting OFF; the library tree has no skeleton/skin module; archives can carry only an optional DCC FPS hint (_ai_DCC_FPS); LICENSE.txt declares BSD 3-Clause using a non-standard SPDX spelling, which plausibly explains GitHub API NOASSERTION (curator observation).
• articleWhat do RenderMan 26's public docs say about Points primitives (shape, falloff, width, camera-facing) that matters for rendering Gaussian splats as points?
  Corrected 2026-10-23 - see C3-B643-03; the original statements below are kept for history and are superseded where the correction says so. RenderMan 26's public docs describe points as disks (with normals) or real spheres (without), sized by constantwidth or per-point width (default 1.0, object space), and list a falloffpower primvar (default 0) for point primitives. None of the pages read documents points:shape, falloffshape, camerafacing, Gaussian falloff or splat rendering. So the override values hdPrman uses for Gaussian splats (seen in earlier reviews) can't be explained from public RenderMan docs.
• articleOverview: for capture to render, what does each file or API in the chain actually carry (markers, blendshape weights, skeleton animation, caches, render products), and what is not carried?
  Synthesis (producer, supported by verified statements): each capture-to-render carrier defines its own fields but not the mapping to the next: C3D labelled markers, ARKit/MediaPipe 52 named coefficients, UsdSkel joints with world-space bind transforms, Alembic time-sampled geometry whose topology may change between samples, UsdRender settings with no universal RenderVar names, and EXR named channels whose layer naming implies no stacking order. None carries a rig, a character or an intent, so marker-to-joint, blendshape-name and RenderVar-to-channel mappings must be authored and recorded.
• articleWhich oiiotool switches and config hints control premultiplied versus unassociated alpha at OpenImageIO v3.2.1.2, and what do the docs warn?
  oiiotool premultiplies unassociated-alpha inputs on read by default; --no-autopremult (or the input config oiio:UnassociatedAlpha=1) keeps them unassociated for subsequent inputs. Colour-transform commands accept :unpremult=1 to un-premultiply around the transform, but default to 0, transforming associated values directly. Combine with CA-B398 for the alpha-0/1 edge behaviour.
• articleWhat does Smith and Blinn (1996) define as the matting equation for constant-colour backings, why is single-backing matting underdetermined, and which failure cases and constraints does it name?
  Smith and Blinn show that pulling a matte from a single constant-colour backing is underdetermined (three colour equations, four unknowns per pixel), so practical keyers rely on constraints about foreground colour (such as no blue, which rules out all greys but black, about two-thirds of hues and all pastels) or need triangulation with two different backings; blue spill, flare, backing shadows and impurities are named practical problems. This is why keyer results depend on assumptions and fail on foreground colours near the screen colour.
• articleWhat OCIO and CLF test data are public at a pin, and what does the repository say about their licence?
  OpenColorIO (22dd9c4f) states that all data under tests/data/files (265 files, about 34 MB, including 7 ICC-named test files) is BSD-3-Clause, copyright OpenColorIO contributors, while THIRD-PARTY.md lists SampleICC under the ICC Software License 0.2 without mentioning the test data; the texts read do not say which governs the ICC test files.
• articleWhat does SeedVR2 document for video restoration (one-step diffusion, GPU needs, scripts) and where does it say it fails or over-sharpens?
  Problem. Restoring or upscaling AI-generated or degraded video without temporal artefacts. Conditions. SeedVR / SeedVR2 (ByteDance Seed; ICLR 2026), Apache 2.0; 3B/7B models. Method. SeedVR2 is a one-step diffusion video restoration model with adaptive window attention that adjusts window size to the output resolution. Inference: torchrun projects/inference_seedvr2_3b.py with --video_path, --output_dir, --seed, --res_h, --res_w and --sp_size (sequence parallel GPUs). Stated capacity: one H100-80G handles a 100-frame 720x1280 video; four H100-80G support 1080p and 2K with sp_size=4; tiling tricks were not yet supported. A community ComfyUI node exists (linked in README). Failure modes (README Limitations). Prototype models; not robust to heavy degradation or very large motions; may fail to remove degradation or generate unpleasing detail; on lightly degraded inputs such as 720p AIGC video it may over-generate detail and oversharpen, especially at small resolutions like 480p. Method (...
• articleHow do I outpaint a still with FLUX Fill or SDXL inpainting in diffusers (strength, mask blur, resolution) and which licences apply?
  Problem. Extending a frame beyond its edges while keeping the original pixels. Conditions. diffusers FluxFillPipeline or an SDXL inpainting checkpoint. Method. (1) FLUX.1 Fill [dev]: the docs say the pipeline supports inpainting and outpainting and does not take a strength input; pass prompt, image, mask_image, height, width and max_sequence_length=512; the BFL doc says the mask must be a black-and-white image the same size as the conditioning image. For outpainting (inference): paste the source on a larger canvas, make the mask white over the new area, and set height/width to the canvas size. (2) SDXL Inpainting 0.1: guidance_scale 8.0, 15-30 steps, and strength=0.99 - the card says to keep strength below 1.0; checkpoint is openrail++. (3) General inpaint tuning from the diffusers guide: strength is how much noise is added to the base image, higher gives more difference from the original; blur_factor on the mask processor softens the seam (example 33); padding_mask_crop crops aroun...
• articleFor 16:9 to 9:16 (or reverse), when should I crop and reframe versus outpaint, what do video outpainting tools document, and how do headroom and lead room constrain it?
  Problem. Delivering a clip in another aspect ratio without losing the framing intent. Conditions. Source clip with fixed composition; vertical (9:16) social delivery as in C3-B573. Tool statements. WaveSpeed's Video Outpainter takes a required video, an optional prompt and an aspect_ratio, expands the video in any direction while preserving motion, identity and scene coherence, and converts ratios without cropping; VACE lists Expand-Anything for video. For stills, getimg.ai says outpainting generates new content around the source while keeping the original pixels unchanged. Craft constraints (Wikipedia). Headroom is the space between the top of the head and the top of the frame and too much creates dead space; lead room is space in front of a subject in the direction it faces or moves. Method (inference). (1) Arithmetic: a centre 9:16 crop of a 16:9 frame keeps (9/16)/(16/9) = 31.6% of the width; if the shot is a wide with several subjects that loses them, so choose reframing by tra...
• articleWhat does the Depthflow ComfyUI node pack provide for 2.5D parallax, what does it pin, and what licence does it carry?
  Problem. Making camera-move parallax animations from a still plus a depth map without a video model. Conditions. akatz-ai/ComfyUI-Depthflow-Nodes commit 1806b6ed (pushed 2026-02-15; not archived), version 1.2.3, licence AGPL-3.0 (LICENSE file and API). Method. The Depthflow node takes an image (or batch) plus a corresponding depth map and applies motion objects (zoom, dolly, circle and others) with optional stackable effects (depth of field, vignette), outputting an image batch to be encoded as video; parameters include num_frames, input_fps/output_fps, quality, ssaa and invert, with tiling_mode. It extends RyanOnTheInside's Flex system. pyproject and requirements pin depthflow==0.9.1 plus pydantic, numpy and opencv-python. The README credits the upstream DepthFlow library by Tremeschin (BrokenSource) and publishes a custom Docker environment image; node documentation lives on an external Notion page. Failure modes. Depth-map quality drives artefacts (the depth source is outside thi...
• articleFrom the FFmpeg filters documentation (R1): multi-input filters such as overlay share "framesync" options, settable only by name. eof_action - what to do when the secondary input hits EOF: "repeat" the last frame (default), "endall" end both streams, or "pass" the main input through untouched....
  From the FFmpeg filters documentation (R1): multi-input filters such as overlay share "framesync" options, settable only by name. eof_action - what to do when the secondary input hits EOF: "repeat" the last frame (default), "endall" end both streams, or "pass" the main input through untouched. shortest=1 forces output to end when the shortest input ends (default 0). repeatlast=1 (default) extends the last frame of secondary streams until the primary stream ends; 0 disables. ts_sync_mode - "default" takes the secondary frame with the nearest lower-or-equal timestamp to each primary frame; "nearest" takes the absolutely nearest timestamp. Overlay note: frames are taken from each input in timestamp order, so if the inputs start at different timestamps, pass both through setpts=PTS-STARTPTS so they begin at zero. Overlay expressions can use t (seconds) and n (frame number) only when eval=frame (default); with eval=init they evaluate to NAN. Practical recipes (derived): logo or watermark...
• articleWhich colour-pipeline outputs does Runway's API document for generated video (ProRes, 10-bit Rec.709, HDR, ACEScg EXR) and what does that say about AI plates in a graded timeline?
  Problem. Default AI video is an 8-bit H.264 MP4, which is thin for grading; which vendors deliver more? Conditions. Runway Dev API docs, fetched 2026-10-23; applies to models gen4.5 and aleph2 as stated. Method (documented fields). outputFormat on the generation request: mp4 (default, H.264), prores (.mov; proresProfile 422 Proxy, 422 LT, 422, 422 HQ, 4444, 4444 XQ; default 4444), png_sequence (.zip of PNG frames plus a .wav when there is audio); these stay SDR. sdr_rec709_10bit gives HEVC Main 10 Rec.709 .mp4 for Gen-4.5 and Aleph 2.0 'when a grade needs more precision than 8-bit H.264'. HDR is Gen-4.5 only: hdr10 (HEVC Main 10, BT.2020 + PQ), hlg, hdr_pq_12bit_master (12-bit 4:4:4 BT.2020 PQ .mov), hdr_prores, hdr_png_sequence (16-bit PNG plus colorimetry sidecar), hdr_exr_sequence (half-float OpenEXR, linear BT.2020 light, 1.0 = 100 nits) and two ACEScg EXR options for ACES 1.3 and ACES 2.0. The ACEScg EXRs are scene-referred by inverting the picture through the ACES Output Trans...
• articleAnswers "should colour scopes/transforms apply to EXR depth or data channels?" from primary docs. OpenEXR (R1): channels are named strings (e.g. R, Z, yVelocity); only R, G, B (intensities) and A (opacity; colour channels premultiplied by convention) have predefined interpretations. Data types:...
  Answers "should colour scopes/transforms apply to EXR depth or data channels?" from primary docs. OpenEXR (R1): channels are named strings (e.g. R, Z, yVelocity); only R, G, B (intensities) and A (opacity; colour channels premultiplied by convention) have predefined interpretations. Data types: HALF for regular image data, FLOAT "where the range or precision of 16-bit number is not sufficient (for example, depth channels)", UINT for "discrete per-pixel data such as object identifiers". Compression: lossy DWAA/DWAB quantise DCT components of RGB data; B44/B44A are lossy for HALF; PXR24 keeps HALF and UINT exact but rounds FLOAT to 24 bits (~3e-5 relative error) and "works well for depth buffers"; lossless ZIP/PIZ-type codecs avoid any change - so put data passes (Z, normals, IDs, motion) in lossless or PXR24-compressed parts, not DWA. Data window vs display window: pixel data may extend beyond (overscan) or within the display window. Colour identification: OpenEXR does no colour tran...
• articleHow do I add dither or film grain before the final 8-bit encode so generated gradients survive compression (FFmpeg sws_dither, noise, libplacebo)?
  Problem. Quantising a smooth gradient to 8 bits without dither creates steps; encoders then flatten low-amplitude noise. Conditions. Last step before an 8-bit delivery encode, working from a higher-bit-depth intermediate. Method. (1) FFmpeg's swscale option sws_dither selects the dither used when converting pixel formats: auto (default), none, bayer, ed (error diffusion), a_dither (arithmetic, addition), x_dither (arithmetic, xor; the doc says more random and less apparent patterning than a_dither). (2) The colorspace filter has its own dither option: none or fsb (Floyd-Steinberg). (3) libplacebo dithers whenever necessary by default; its modes include none (the doc warns this may result in visible banding), bayer ordered, blue_noise and floyd_steinberg. (4) Grain: the noise filter adds noise per component with strength 0 to 100 (default 0, so nothing happens unless set) and flags a (averaged temporal, smoother), p (mix with regular pattern), t (temporal: pattern changes between fra...
• articleWhich OpenEXR header attributes carry colour meaning, which one is now preferred, and how should readers and writers treat them?
  Scope: attribute inventory only; for reader behaviour see the OpenEXR reader-rules record C2-B16-B2-01. As an inventory, the five optional colour attributes at OpenEXR v3.5.2 and the chromaticities-superseded note are confirmed in pinned bytes (same bytes as S3 of C2-B16-B2-01).
• articleWorld Labs Marble (Oct 2026): persistent 3D worlds from text, images, video or a 3D blockout - models, credit costs, plan rights and export paths
  Primary docs. Marble generates persistent 3D worlds (Gaussian splats, optional meshes) from a text prompt, single image, multiple images, 360 panorama, video, or a coarse 3D layout built in "Chisel" (draw walls, doorways, place a panorama camera, or upload GLB/FBX geometry, then prompt). Studio tools: Compose (join several worlds into larger environments), Record (camera flythroughs exported as video), pano edit, Expand (fix low-fidelity regions/grow worlds), variations. Models (R1): Marble 1.1 (recommended, 1,500 credits per world), Marble 1.1 Plus (largest worlds; 1,500 base + 0-1,500 variable), Marble 1.0 legacy (1,500), Marble 1.0 Draft (150 credits, fast tests) - 1.1/1.1 Plus added 2026-04-02 (R2). Credit examples (R3): single-image world = 1,500 + 80 input credits; edits 150 per pano edit; expand 2,000. Plans: Free (text/single image/pano, up to 4 worlds), Standard (multi-image, video and 3D-layout inputs, editing, export; ~12 worlds), Pro (expand, enhanced video output, high-...
• articleCoverage note with small facts: 11 more sponsored or self-promotional Mikkel Lassalle uploads (Feb-Mar 2026)
  Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Concrete items: Artlist platform tour (2026-03-12, R6) - claims 50M creators; video tools with negative prompts, multiple references, multi-output, four cinematic styles and clip chaining into a long scene; custom voice cloning from about 10 seconds of audio (consent rules apply). Artlist "Big Ad" challenge with a $60,000 prize (R12) - contests as a sponsor marketing tactic. Enter.pro (R2): an "AI development agent" test building a deployable app with payments in about an hour; it recommended Gemini 3 Pro or Claude Sonnet 4.5 for the app's text generation; he configured a freemium plan (5 free shot plans/month, unlimited on Pro). Framia Pro (R1): agent platform with cre...
• articleTool snapshots from mid-2026 sponsored walkthroughs: Meshy texturing options, Lumina canvas planning, Artlist preset apps, Pippit "story series" pitch
  Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Meshy (2026-07-30): image-to-3D "quick generate" or agent mode; standard vs "smart topology"; texture step with options to remove baked lighting, generate PBR maps, and texture resolution 2K/4K/8K. Lumina canvas (2026-08-04): describe the story -> auto storyboard of individual shots -> "director's desk" to set framing, composition, camera movement and key shots before generating (claims no queue waiting). Artlist "AI apps" (2026-07-01): 70+ one-click presets in categories (viral, editing tools, camera movement, product, typography, social, collabs) - e.g. product photo -> lifestyle shot or packaging mockup. Pippit Story Studio with Seedance 2.5 (2026-08-20): script/scre...
• articleAgentic all-in-one AI video platforms (SekoTV) and image-to-3D platforms (Hi3D): what the workflows look like
  Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. SekoTV (sponsored, 2026-09-22): a "creation agent" with skill templates (cinematic one-take short, character concept board, TVC product ad, master director, etc.) takes a one-line idea, proposes a configuration (tone, aspect) and three plot options, writes asset prompts, generates assets with GPT Image 2, waits for "confirm visual assets", then writes and runs the final one-take video prompt with sound; models offered include Seedream 5.0 Pro, GPT Image 2.5, Nano Banana Pro. Human checkpoints shown are confirmation gates rather than prompt edits. Hi3D (sponsored, 2026-09-29): text-to-image (Nano Banana 2 recommended; a clean grey background helps) then image-to-3D with ...
• articleWhat can AI agents do inside an editing workflow today (trimming, synthetic B-cam angles, motion graphics, LUT grading, sound), and where do they fail?
  Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Dan Kieft (2026-09-29, Higgsfield-sponsored) uses a desktop chat agent ("GPT Astra", as he names it) with MCPs for Higgsfield, DaVinci Resolve (paid version) and Blender, plus computer-use control of Premiere Pro/After Effects: (1) trim dead space from transcription, insert editor-note adjustment layers and mark candidate B-cam/C-cam spots - works but slow (about 14 minutes for some trims via screen control; the Resolve MCP is much faster) and needs monitoring; local desktop app needed for large camera files (cloud upload limit 512 MB); (2) synthetic B/C-cam angles: give a photo of the room and the A-cam clip, generate side angles with Seedance 2.5 (plausible shadows an...
• articleHow was a large-scale ocean/kaiju water shot simulated in Houdini (particle counts, wedging), as a traditional VFX reference point?
  Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. In a short making-of (2026-01-16) Mikkel Lassalle reports his kaiju ocean shot used a Houdini FLIP simulation of about 50 million particles plus about 70 million whitewater particles; to make the whitewater feasible he split the FLIP tank into four wedges, simulated each separately, and combined them at render; the environment was matte paintings composited in After Effects with "simple blend modes and color corrections" (method transferable to Nuke/Fusion); HUD graphics also in After Effects; creature by a collaborating 3D artist, music/sound by another collaborator. Value: a concrete scale/time reference to contrast with AI-generated water "for free" in layout-to-rend...
• articleHow do compositors use video-to-video AI for VFX tasks (insert, remove, replace objects; new angles) while keeping plate motion?
  Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. A senior compositor (2026-06-07, Artlist-sponsored, Seedance 2.0) shows a hybrid VFX pattern: upload the plate as a video reference and lead the prompt with "preserve the clip 100%" (or "preserve the clip's motion 100%") then state one change: add sharks around a surfer; a shark attack; remove a black Porsche; replace it with a golden Lamborghini; collapse buildings with "realistic debris simulation, dust interaction, high dynamic range, grounded physics"; a meteor strike; relight to night and add a spacecraft (reflections in a lake were handled plausibly). Each clip took about 2 minutes; expect several takes (one take changed the camera angle, one mis-timed the action)...
• articleHow can you do markerless AI performance capture (turn an actor into a creature) with masked video-to-video, and what goes wrong?
  Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Mickmumpitz (2026-10-07) uses MiniMax H3's reference variant in ComfyUI: feed the original performance video, lock audio to the source, and in-paint only inside a mask (auto-mask from text such as "head, helmet, phone, cable" or a manual Resolve/After Effects matte) so the camera stays locked and the result composites over the plate. Identity is fixed with a character sheet; expressive emotion sheets gave much better facial performance than neutral sheets ("keep the character's identity, look, and art style from picture number one"). Findings: mask size drives head size; full-body masks enable whole-body transformation; partial masks spanning head and lower body produce...
• articleHow do you build a local AI VFX shot pipeline with mask + driving video + control nets + reference images (Wan VACE/Phantom merge), and what fails?
  Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Mickmumpitz (2026-03-30) uses a community merge of Wan 2.1 VACE (in/outpainting guided by depth, Canny edges, pose) with Phantom (up to four reference images for identity), published as Inner-Reflections/Wan2.1_VACE_Phantom. Building blocks: (1) black-and-white mask (only white is regenerated), (2) driving video = modified plate + control signal, (3) reference images (one = start frame; more = style freedom), (4) detailed prompt (LLM-"proofed" but without camera description). Controls: tracking markers drawn as white squares let the model reproduce camera motion; Canny keeps exact detail, depth allows more new detail; OpenPose plus a back-view reference kept a creature ...
• articleHow does 4D Anyone create a 4D Gaussian-splat capture of a person from one phone video, and what are its limits in a ComfyUI port?
  Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Mickmumpitz (2026-09-11) ports the 4D Anyone paper (ant-research, Apache-2.0 repo) to ComfyUI: from one (ideally tripod) vertical phone video, a 3D skeleton locks pose per frame and a fine-tuned video model generates up to ~48 consistent synthetic views (it keeps already-generated angles in context and reshuffles which views generate together: far-apart first for shape, neighbours later for smooth transitions), then gsplat trains per-frame Gaussian splats. He swapped the original skeleton code (not licensed for commercial production) for Meta SAM 3D Body (SAM License) and bundled a gsplat setup script. Settings: camera preset (high-quality vs quick 16-view), Turbo on (l...
• articleWhat do the Nuke 17.1v2 docs say CopyCat, Inference, Cattery, CatFileCreator and BigCat do for rotoscoping, how should the training data be built, and how do they tell you to fix bad mattes?
  Partially verified: the curator re-read none of the cited sources; S17, S19, S20, S22, S18, S25, S23, S24 rest on the producer's pinned reading. In Foundry's Nuke 17.1v2 documentation CopyCat is a NukeX/Nuke Studio node that trains a per-shot network from a few Input/Ground Truth frame pairs (for example six frames and six hand-made roto masks) and writes a .cat file that the Inference node applies to the whole sequence. The docs call for diverse frames, matched pair order, faked extra pairs for shadows or defocus not in the data set, checkpoints for retraining, and Grade/RotoPaint cleanup of artifacts; they offer a "Human Matting" initial-weights option. BigCat is a separate node for generalising across many shots, and the docs say CopyCat deliberately overfits one shot. The pages give no accuracy numbers, and the Cattery page describes a library of third-party models whose listing is JavaScript-only (not read).
• articleIf a pipeline ingests VES Camera Report CSV, what parsing rules does the spec give, which fields and versions are inconsistent or unfinished, and what evidence is there that vendors adopted it?
  The CRIF spec gives parse rules (CSV, one row per take with slate columns repeated, SlatesUUID as dedupe key, 'Tk ' take prefix, vertical-tab multi-selects, YYYY/MM/DD timestamps, SLATE-CAMERALETTER file names). It also has unfinished or inconsistent parts: footer 'v0.9c 9/25/2013' versus table 'Version 1.1', a 'Start Height' help text on the End field, mixed feet/inches strings under a numeric-only rule, a TODO on Tk Clip Num, provisional stereo fields. Adoption evidence is vendor pledges (press release, 2013) and two listed integrations; no later adoption record was found in the files read.
• articleAt pinned revisions, what must a reader of an OpenEXR file do about colour space, where do the ColorInterop prose and its Figure 2 flowchart (and OpenEXR docs) disagree, and what is the conservative reading?
  At the pins (ColorInterop 8b7b15cc v1.0.0; OpenEXR 69b2604f v3.5.2; OIIO febb1748) the recommendation prose keys on the attribute 'acesImageContainer' being present, its flowchart on the flag being 'set', while OpenEXR docs/core name it acesImageContainerFlag and require int value 1, and OIIO tests == 1. All bytes match producer pins. For a header with acesImageContainerFlag = 0, a literal reading of the prose yields ACES2065-1 while the flowchart, OpenEXR docs and OIIO yield not-ACES (curator agrees this is the plain reading; synthesis, not tested). Prose both permits fallback for an unrecognised ID and says the failure should ideally be surfaced; the flowchart shows only the fallback path at node J.

More