2D/3D animation, rigs, retargeting, motion capture, facial animation and lip sync
- articleWhat do scholarly sources say about improvisation, audience interaction and the use of painted screens (pardeh) in naqqali, and what could a contemporary narrator responsibly take from it?
Evidence is thin and indirect. Khosravi (2025, citing Aydenloo 2011) reports that storytellers in public sessions reinterpreted story aspects based on shared values with the audience or improvised new elements inspired by the context, and her Persian background (citing Mills 2001 and Page 1992) notes narrators sometimes improvised a forbidden topic into the middle of a session; training was by imitation of masters, refined by audience feedback. Galehdaran and Pourzarrin's English abstract (2019) says in pardeh-khani the narrator, 'with skill in improvisation', identifies the figures on the screen with the actual environment, masks parts of the screen and places himself as a visual element, with performance either in closed courtyards or open air where a scroll is opened slowly or a cover screen removed. Page's 1979 field-based article on transmission is paywalled; only its extract is readable. UNESCO's text was not readable.
- articleWhat body and gesture conventions are documented for the naqqal, what changed from the old manual to modern practice, and how do two named masters differ in one battle scene?
Khosravi (2025) compares recorded performances of the Rostam-Sohrab second wrestling scene by Masters Saeedi (film c.2000) and Torabi (film 2009) using Muller's (2024) co-speech gesture toolbox. She counts 23 gestures for Torabi (5 functional, 18 depictive) and 22 for Saeedi (7 functional, 15 depictive); Torabi stresses the physical fight and fate (the 'wheel of fortune'); Saeedi uses more abstract and functional gestures, stresses Sohrab's resistance, repeats the phrase 'he only bent Sohrab's back', and presents the death as a tree felled by wind, making Rostam accountable. The article's Persian background reports that the historical manual Taraz al-Akhbar (cited via Haj Seyed Javadi) tells the storyteller not to illustrate with body gestures, with limited battle-scene exceptions, so modern gesture practice contradicts the manual's rule as quoted.
- articleWhat is naqqali (Iranian dramatic storytelling of the Shahnameh), how does it differ from Shahnameh-khani, and what do 'scroll' and 'pardeh' mean in this context?
Open scholarly abstracts and an English-and-Persian 2025 article agree on the core: naqqali is performed narration of stories, today above all of the Shahnameh, as distinct from Shahnameh-khani, which is reciting the verses themselves. Jahandideh and Khaefi (2013) define naqqali of the Shahnameh as narrating with special tone, feelings, expression, gestures and movements, and Shahnameh-khani as singing the exact verses; they report four basic types. Khosravi (2025) says the form's peak is placed in the 10th-13th centuries (as printed, solar Hijri) and that from the late Qajar period it narrowed to prose manuscripts (tumars) built on the Shahnameh. The word 'scroll' is used for two different things: the narrator's written prose tumar (Khosravi, citing Aydenloo) and the painted pardeh used in pardeh-khani (Galehdaran and Pourzarrin 2019). UNESCO's inscription files were not readable.
- articleUnder the Move One App EULA, who owns the mocap Output, what may I do with it commercially, and what may I not do with it (AI training, competing products)?
At the Move One App EULA page fetched 2026-10-22 (header Last-Modified 2026-10-22T01:02:33Z), Move AI owns the IP in the Motion Data and Output (7.1.2) and licenses the Output back to the user worldwide, royalty-free, transferable and sublicensable (7.3), but the licence is void if Output is put to a defined Prohibited Use (7.5): building a competing product, training any AI System, or using it as an input to an AI System other than to create an original video work. The user in turn grants Move a perpetual, irrevocable licence to uploaded video for providing services and for developing and training its products (7.2). This is clause reading only, not legal advice or clearance.
- articleDoes the Alembic project publish sample .abc files, and what terms cover them?
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.
- articleWhat 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?
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.
- articleBeyond SFU, ACCAD, CMU and KIT, which further AMASS component datasets state their own licence on public pages, and what do they say?
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.
- articleWhich 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?
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.
- articleWhat must a custom character satisfy to be used in Flow Studio, which terms govern its outputs, and how have the documented capabilities changed over recent dated releases?
The character requirements page (stamped Oct 19, 2026) sets file, polygon, hair-strand and DCC-version limits, T-pose and add-on validation requirements. The release notes show the platform broadening in 2026 from live-action replacement into a 3D Editor and a Canvas that hosts third-party generative video/audio models, so "Flow Studio" now covers more than the original tool. Output ownership is not stated on the pages read: the only terms linked from the help site are Autodesk's General Terms (Internet Archive snapshot 2026-10-16), which say users keep ownership of what they submit, define "Output", and disclaim responsibility for it; product-specific Special Terms were not read, so Flow Studio output rights remain unresolved.
- articleWhat does the VRM Public License 1.0 text itself state, and how does it hand control to the per-model "License Settings"?
The VRM Public License 1.0 (English page at vrm.dev/en/licenses/1.0/) grants Model Use and makes other rights depend on the License Settings stored in each VRM file; the alternative URL form vrm.dev/licenses/1.0/en/ returned 404 to curator GET, consistent with the producer observation.
- articleWhich machine-readable licence and usage fields does VRM 1.0 (VRMC_vrm.meta) define, and how do they differ from VRM 0.x meta?
VRM 1.0 meta requires name, authors and licenseUrl and defaults to restrictive values (onlyAuthor, personalNonProfit, credit required, modification prohibited, redistribution false), so an absent field is not a permission; VRM 0.x field names keep the misspelling "Ussage", which parsers must match literally.
- articleHow do animatic durations stored in milliseconds, seconds or H:MM:SS:FF convert to frame-exact exposures, and where can rounding drift occur on export?
Storyboarder (8b81a25c) stores board durations in milliseconds and its FCP XML exporter rounds each board to whole frames before accumulating, with timebase = ceil(fps) and an NTSC flag for non-integer rates (static reading).
- articleHow does the Japanese-method digital timesheet workflow (24-frame seconds, 3-frame holds, empty cells, .xdts exchange) work, as described by a studio-method tutorial?
A CELSYS tutorial describing Nippon Animation's digital drawing method sets the timeline to 24 frames per second, reads it horizontally (unlike paper sheets) and exchanges timesheet data as .xdts between the digital timesheet editor and CLIP STUDIO PAINT (Japanese original reinspected).
- articleWhich classic craft concepts (key, breakdown, in-between, spacing, holds) do the AI in-betweening tasks actually correspond to, and is any production use documented?
Editor's mapping (synthesis, not stated by any source): the papers' "given frames" are Lutz's extremes/keys; the generated frames are in-betweens; ToonComposer's optional middle sketch plays the role of a middle (breakdown-like) key; spacing is controlled only implicitly (sketch positions, FPS conditioning, text) and holds and exposure (on twos) are not modelled in either ToonCrafter or ToonComposer (no hit for hold, twos, spacing, timing, breakdown or exposure in either paper body). No production use is documented in the sources read: ToonComposer thanks two studios for permission to use footage in evaluation; ToonCrafter calls itself a research exploration. Production use is therefore a hypothesis here.
- articleWhat do the earlier AI in-betweening papers (AnimeInterp 2021, AnimeInbet 2023) and AniDoc (2024) claim about inputs, failure modes and data, and what licences do their code, weights and datasets carry?
Abstract- and README-level only (full papers not read for storage reasons). AnimeInterp: raster-frame interpolation of one in-between from two frames, framed around textureless flat regions and large non-linear motion, with the ATD-12K triplet dataset. AnimeInbet: vector/line-graph inbetweening of black-and-white line drawings, because raster warping blurs lines; ML240 dataset of 244 sequences; Chamfer distance code. AniDoc: video-diffusion colourisation of sketch sequences, with in-betweening from start and end sketches. Terms: AnimeInterp code MIT by README only; AnimeInbet dataset CC BY-NC-SA 4.0 and code non-commercial; weights and AnimeInterp data links carry no terms in the READMEs.
- articleWhat does ToonComposer (2025) claim for AI "post-keyframing" from sparse keyframe sketches, what was measured on real artist sketches, and what are its failure modes and licences?
ToonComposer (arXiv v1, Aug 2025) merges in-betweening and colouring into one step on a Wan2.1 video model: a colour reference frame plus one or more keyframe sketches (any frame position) and optional region masks produce the clip. Evaluation: synthetic benchmark from cartoon films used with permission, PKBench (30 scenes, start/end sketches drawn by professional artists) and a 47-person preference study (70.99% aesthetic, 68.58% motion for ToonComposer). Stated problems: baselines distort faces and are sensitive to bold line styles; blank sketch regions render flat unless region masks are used; compute cost (README: 61 frames at 480p needs ~57 GB VRAM). Licence statement is MIT including weights.
- articleWhat does ToonCrafter claim and measure for generative cartoon in-betweening (inputs, frame counts, metrics, user study, failure modes) and what are the code/weights/data terms?
ToonCrafter (arXiv v1, May 2024; SIGGRAPH Asia 2024 journal track per README) generates intermediate frames between two cartoon images with a fine-tuned image-to-video diffusion model, optionally guided by sparse sketches. Released model: 16 frames at 512x320 from a start and end image plus text. On its own 1K cartoon test set it reports FVD 43.92 vs 98.96 for the next best (SEINE) and a 24-person study with 68.98% preference for motion quality; it does not win LPIPS (0.1733 vs 0.1702 FILM). Stated failure modes: baselines fail on dis-occlusion and non-linear motion; unadapted priors leak live-action content; compressed latents cause flicker/detail loss; the maintainers state the success rate is not guaranteed.
- articleWhere have learned models been documented for line work in a drawn-look pipeline (production vs research vs open tools), and what are their inputs, limits and terms?
Documented production use: Sony Pictures Imageworks trained a scikit-learn GradientBoostingRegressor inside Houdini to predict how artist-drawn ink lines should adjust with camera angle and expression, ~600 frames per character first generation, with artists nudging the prediction (account by Grochola via fxguide, 2019). This model moves hand-drawn lines on 3D animation; it does not extract lines from images. Research/open line extractors differ: Informative Drawings (arXiv 2203.12691v3) maps photographs to line drawings, with a stated dependence on a pretrained depth network; ControlNet 1.1 lineart models use extracted or hand-drawn lines to steer image generation. None of the two research/open sources documents use on 3D character renders.
- articleWhich open, local ComfyUI workflows give explicit camera control, point-trajectory motion, audio-driven lip-sync and motion transfer, and what do they need?
ComfyUI official tutorials (captured 2026-10-23), all Wan-family (Wan licences Apache-2.0 for 2.x per C3-B370-03; check each repo): (1) Wan2.2 Fun Camera Control (alibaba-pai/Wan2.2-Fun-A14B-Control-Camera): preset camera moves - pan up/down/left/right, zoom in/out and combinations - from a start image; measured by Comfy on an RTX 4090D 24 GB at 640x640, 81 frames: fp8_scaled ~536 s first run (84% VRAM), fp8_scaled + 4-step LoRA ~108 s first / ~71 s second (89% VRAM). (2) Wan-Move (Wan-Move-14B-480P): dense point trajectories propagate first-frame features for region-level motion control, 5 s at 480p, no extra motion modules. (3) Wan2.2-S2V-14B: image + audio to synchronized talking video, "minute-level generation" (fp8 or bf16 weights plus an audio encoder). (4) InfiniteTalk (on Wan2.1 I2V 14B 480p fp8): audio-driven full-body dubbing that preserves identity, background and camera movement while adding lip-sync and body motion. (5) Wan Animate 2: motion transfer from a driving vide...
- articleHow does SAG-AFTRA's 2026 MOA define a 'Synthetic' performer made with generative AI, what notice/bargaining timeline does it set, and what does it say about training-data licences?
The 2026 MOA defines a Synthetic performer by four elements (not recognisable as an identifiable performer, not voiced by a natural person, not a digital replica, no employment arrangement for the role). Using one in a human role requires that it bring significant additional value, prior written notice and a ten-business-day meeting, with outer limits and arbitration limited to remuneration paid to the union health or pension plan; that paragraph expires 30 June 2030 (producer reading for the expiry and facial-feature consent rule).
- articleWhat do Sync Labs lip-sync models document for inputs, face constraints, duration limits and price (Oct 2026)?
Sync Labs docs (captured 2026-10-23) list lipsync-2, lipsync-2-pro and sync-3 plus legacy lipsync-1.9.0-beta. lipsync-2/2-pro render faces at 512x512 (fine for most 1080p; large faces look softer), infer in independent 2-second chunks and need natural speaking motion in the input video: still-frame segments get no lip motion. Obstruction detection is optional on 2/2-pro (slower), built into sync-3, which also handles profiles/over-shoulder and outputs 4K. For multiple faces, mask or crop externally. Max duration depends on plan, 1 min (Hobbyist) to 30 min (Scale+); free tier 3 generations/month, 20 s each (sync-3: 1 generation, 15 s). Per-second prices at 25 fps: 1.9 beta $0.02-0.025, lipsync-2 $0.04-0.05, 2-pro $0.067-0.083, sync-3 $0.107-0.133. Isolate vocals for song lip-sync. Open alternative: LatentSync 1.6 (Apache-2.0 repo, 2025-06) needs 18 GB VRAM for inference (1.5: 8 GB), trained at 512x512, and its pipeline uses InsightFace landmarks (InsightFace pretrained models carry t...
- articleWhat does PersonaShot report about character identity, physical state and emotion across cuts in multi-shot video, and how do open and closed systems compare?
PersonaShot (arXiv 2608.16717v1, 17 Aug 2026) has about 1,000 multi-shot segments and 16 metrics; Identity Consistency (ID) is tracked-character cross-shot embedding similarity. In its Table 2 (shot-level prompts) ID is Seedance 0.673, HoloCine 0.582, LTX-2.3 0.572, MultiShotMaster 0.557, EchoShot 0.463; under global prompts ID is LTX-2.3 0.697, VGoT 0.683, Seedance 0.642. The headline finding is that visual fidelity does not predict continuity: ShotStream has VF 0.994 but aggregate 0.601, and the authors say physical-state resets and abrupt affective shifts persist even in good-looking videos. Three specialist evaluators (distilled from Qwen3.5-397B into Qwen3.5-4B LoRA) correlate 0.69-0.75 with human MOS. No code or data link was found.
- sourceVRM specification (avatar format with license metadata)
- sourceyohanshin/WHAM
- sourceTMElyralab/MuseTalk
- sourceTencent/MimicMotion
- sourceshubham-goel/4D-Humans (HMR 2.0)
- sourceRudrabha/Wav2Lip
- sourceOpenTalker/SadTalker
- sourceMMPose RTMPose project (open-mmlab/mmpose)
- sourceMakeHuman
- sourceIDEA-Research/DWPose
- sourceGuyTevet/motion-diffusion-model (MDM)
- sourcegoogle-ai-edge/mediapipe
- sourcefudan-generative-vision/hallo2
- sourcefacebookresearch/sapiens2
- sourcefacebookresearch/sapiens
- sourceCMU-Perceptual-Computing-Lab/openpose
- sourcebytedance/LatentSync
- sourceantgroup/echomimic
- sourceali-vilab/UniAnimate
- discussionThe SDK Release License page does not define small scale. The Proprietary Software License Agreement Version 2.1 (revised 2025-02-03) defines Small-Scale Enterprises as latest sales under 10 million yen, Middle-Scale as 10 million yen or more and under 100 million yen, and Large-Scale as 100 millio…
- discussionCode: BSD 3-Clause (LICENSE.txt) for files outside thirdparty/ and the MyPaint brush directory; GitHub shows NOASSERTION because the file has extra notices. Third-party code and brush sets carry their own licenses. The user manual repository has no LICENSE file; its README says CC-BY-NC 4.0, i.e. n…
- discussionFigures differ by survey year and population, not necessarily by contradiction. The AJA statement cites the JAniCA 2022 survey: average annual income of 1.966 million yen for ages 20-24 and 4.555 million yen overall, and says the UN working-group figure of 1.5 million yen for new animators traces t…
- discussionMethod. 1. Read meta.licenseUrl; in VRM 1.0 it accepts https://vrm.dev/licenses/1.0/, the VRM Public License document 1.0 (enacted 2021-08-05), which binds users to the licensor's 'license settings' written in the avatar. 2. Read the per-avatar meta fields and their defaults: avatarPermission (only…
- discussionMethod. Steps 1-8 are stated in the MHLW handout by a JAniCA lawyer-auditor (2023); step 9 is the collector's inference. 1. Pre-production: scenario, character and world settings are produced and the director or 演出 draws the 絵コンテ, the keystone that records acting, movement timing, backgrounds, dial…
- discussionWhich Japanese institutional source defines タイムシート (exposure sheet) and says who prepares it and when in TV anime production?
- discussionWhat is the effective date and full definition of 'Expandable Application' in the Live2D publication license, and does a Live2D-rigged VTuber avatar always fall under it?
- sourceVRMパブリック・ライセンス文書 1.0 (VRM Public License document 1.0; vrm.dev)
- sourceUniVRM (vrm-c/UniVRM): VRM and glTF 2.0 import/export for Unity