Pith. sign in

REVIEW 7 cited by

Keyframer: Empowering Animation Design using Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.06071 v2 pith:WTZHKBFD submitted 2024-02-08 cs.HC

Keyframer: Empowering Animation Design using Large Language Models

classification cs.HC
keywords designanimationanimationslanguageiterativekeyframernaturalresponse
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Creating 2D animations is a complex, iterative process requiring continuous adjustments to movement, timing, and coordination of multiple elements within a scene. To support designers of varying levels of experience with animation design and implementation, we developed Keyframer, a design tool that generates animation code in response to natural language prompts, enabling users to preview rendered animations inline and edit them directly through provided editors. Through a user study with 13 novices and experts in animation design and programming, we contribute 1) a categorization of semantic prompt types for describing motion and identification of a 'decomposed' prompting style where users continually adapt their goals in response to generated output; and 2) design insights on supporting iterative refinement of animations through the combination of direct editing and natural language interfaces.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. LiveSVG: Zero-Shot SVG Animation via Video Generation

    cs.CV 2026-05 unverdicted novelty 7.0

    LiveSVG fits original SVG paths to a generated target video via dual-level motion (group homographies plus per-path Bezier offsets) and sphere-packing recolorization to achieve zero-shot, skeleton-free SVG animation.

  2. VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation

    cs.CV 2026-05 unverdicted novelty 7.0

    VAnim creates open-domain text-to-SVG animations via sparse state updates on a persistent DOM tree, identification-first planning, and rendering-aware RL with a new 134k-example benchmark.

  3. LottieGPT: Tokenizing Vector Animation for Autoregressive Generation

    cs.CV 2026-04 unverdicted novelty 7.0

    LottieGPT tokenizes Lottie animations into compact sequences and fine-tunes Qwen-VL to autoregressively generate coherent vector animations from natural language or visual prompts, outperforming prior SVG models.

  4. fog: Expressing Motion and Emotion through Function Composition of AI-Generated Code

    cs.HC 2026-07 conditional novelty 6.0

    fog composes LLM-generated motion functions (verbs/adverbs/gestures/emotions) so people recognize intended semantics in Heider-Simmel animations at 68% accuracy and iterate faster than pure prompting.

  5. Flowcode: An AI-Powered Programming Environment for Scaffolding Iteration in Creative Computing Education

    cs.HC 2026-07 conditional novelty 6.0

    An iterative design of Flowcode shows that LLM-generated flowcharts plus step-by-step fill-in-the-blank explanations help novices orient, navigate, and extend found creative-coding projects.

  6. DataSway: Vivifying Metaphoric Visualization with Animation Clip Generation and Coordination

    cs.HC 2025-07 unverdicted novelty 6.0

    DataSway supports creation of semantically aligned animations for metaphoric data visualizations by generating clips via VLMs and coordinating timelines based on entity order, attributes, layout, or randomness.

  7. Understanding the Human-LLM Dynamic: A Literature Survey of LLM Use in Programming Tasks

    cs.SE 2024-10 unverdicted novelty 3.0

    A survey of user studies on LLM use in programming that identifies interaction behaviors, mixed benefits and weaknesses, and factors influencing human and task performance.