moh4696/open-3d-skills

motion-assets

Plans and generates the images and video clips an animated website needs with AI image and video models, without wasting money.

Ver código fuente

Cómo usar

  1. Copia el comando y revisa el paquete antes de instalarlo en tu entorno de agente.
  2. Consulta las herramientas, credenciales y entornos necesarios en el documento original.
  3. Describe las entradas y el resultado deseado; contrasta la salida con las fuentes.
npx skills add https://github.com/moh4696/open-3d-skills --skill motion-assets

Antes de empezar

  • La instalación no incluye suscripción al modelo, cuota API ni permisos sobre tus archivos.
  • Las estrellas e instalaciones reflejan actividad, no una prueba independiente de calidad o seguridad.
Documento original del Skill

Contenido del repositorio de origen con títulos, ejemplos, código, tablas, enlaces e imágenes preservados.

Motion assets

Generated assets make or break an animated site, and they cost real money per attempt. This skill is the production discipline around the models: decide everything that can be decided before spending, make every asset in one look, generate in the order that lets later assets anchor on earlier ones, check each one with numbers, and write it all down.

Tools

ScriptWhat it does
scripts/loop_check.pyScores how well a clip loops, finds the best loop point, trims and cross-fades it
scripts/paste_back.pyPuts the original pixels back into an outpainted image (outpainting re-renders the middle too)

Related: alpha-cutout (clips that need transparency), scroll-film (prep.py seams scores joins between chained clips), cursor-rig (head-turn clips).

Needs Python 3.9+, pip install numpy opencv-python-headless, ffmpeg.

Before spending anything

Write a short plan and show it to the person paying:

  1. The concept in two sentences, and what moves on the page.
  2. The asset list: every image and clip, its size and aspect, its role on the page, and its exact prompt.
  3. The model for each, chosen by capability (table below), and the cost of each and in total. Calibrate first: run one still and one short clip, read what was charged, then estimate the rest from that. Plans and prices change; never quote a price from memory.
  4. What the visitor sees with reduced motion and on a phone.

Get a yes, then generate.

Choose models by capability

You needThe model must supportNotes
A clip that ends on a planned frameStart frame and end frameEssential for chained scroll films, head turns and loops
A seamless loopStart = end frameThen check with loop_check.py; models rarely land exactly
A pose or expression change on the same characterImage editing that holds framingCompare to the source at full size: only the edited part may change
A transparent subjectNothing special: shoot on a key plateSee alpha-cutout. A few image models return real alpha; video models do not
Wider artworkOutpaintingIt re-renders the original area: paste it back (paste_back.py)
SharpnessNative resolutionNever upscale a clip and call it 1080p; encode what the model returned

Observed while building with these models in 2026 (check current docs; behaviour changes):

  • Video models drift a flat background colour within a single clip (pure magenta came back pale pink); key per frame.
  • Models change small details mid-clip (a black cap turned green late in a serve). Watch the whole clip, not the first and last frames.
  • Some higher resolutions and quality modes are gated by subscription plan. A rejected submission usually costs nothing: test the cheapest request that proves access.
  • Rate limits are tight on many plans: two or three video jobs in flight. Submit in small batches and resubmit only the job that returned 429 once others finish.
  • A "server not responding" error does not always mean no job was created. List recent jobs before resubmitting, or you pay twice.
  • A request can come back as a suggested preset instead of a job; decline the preset and resubmit.

One look across every asset

  • Write a style preamble (medium, palette, light, lens, texture) once and prepend it byte-for-byte to every image prompt.
  • Make one hero still first, approve it, then pass it as the style reference to every later image.
  • Use one video model for a whole chain of clips. Each model has its own motion, colour and grain; switching mid-film shows as a style jump at the seam.

Generation order

  1. Stills: hero, then keyframes (every start and end frame of every clip), then supporting images. Review them side by side before any video.
  2. Clips, each anchored on approved stills. For chains, anchor each clip's start on the exact extracted last frame of the previous clip, not on the still, so colour drift does not accumulate as a jump.
  3. Check every clip: loop_check.py for loops, scroll-film/scripts/prep.py seams for chains, the whole clip by eye for detail drift.

Clip prompts that behave:

  • Name the camera: "locked-off camera" or the exact move ("slow push in, no rotation").
  • Name what must not move: "the body, background and lighting stay perfectly still".
  • For loops: "constant, even motion; no slowing down at the end". Models ease to a stop by default, which hitches every loop. loop_check.py reports it.
  • Repeat the plate colour for anything that will be keyed.

Fixing instead of regenerating

ProblemFix
Loop jumps slightlyloop_check.py clip.mp4 --fix loop.mp4 cuts at the best loop point; add --blend 6 to cross-fade small drift
Loop jumps a lot (over ~8)Regenerate with start = end frame and the constant-motion wording
Outpaint softened the subjectpaste_back.py original.png extended.png out.png
Seam between chained clipsRegenerate the later clip from the extracted last frame of the earlier one
One detail changes colour mid-clipRecolour that hue in post if it is isolated; otherwise regenerate

Log everything

Every generation goes in prompts/asset-prompts.md (and machine-readable in a JSONL log): the asset name, model, exact prompt, input images, settings, job id, cost, and which output was kept. It is the only way to regenerate one asset months later in the same style, and the honest record of what was AI-generated.

del mismo repositorio

Más Skills

Todos los Skills
moh4696
Comunidad

alpha-cutout

Turns an AI-generated (or filmed) clip of a character or product into a transparent, web-ready animation by shooting it on a flat chroma plate and keying it with per-frame plate measurement and edge unmixing. Delivers stacked-alpha MP4 that plays with transparency in every browser including Safari, VP9 alpha WebM, or keyed WebP frame sequences for scroll scrubbing. Use when an animated subject has to sit over page content, between layers of type, or over a 3D scene, when someone asks for "transp

Instalaciones / 1h
1
GitHub Stars
443
Actualizado
9 nov
moh4696
Comunidad

cursor-rig

Makes a painted or illustrated character turn its head to follow the visitor's cursor, looking like one continuous painting that moves, without a 3D model or face tracking. Generates head-pose keyframes with an image-editing model and head-turn clips with an image-to-video model, then builds a pose grid on one fixed body (selected by measured head position, aligned, masked, with optical-flow in-betweens) and plays it with a spring-driven canvas player that also blinks. Use when someone wants a h

Instalaciones / 1h
1
GitHub Stars
443
Actualizado
9 nov
moh4696
Comunidad

scroll-film

Builds scroll-scrubbed film sections, where scrolling plays a pre-rendered camera move, a product turning, a liquid pour or a fly-through one exact frame at a time, from AI-generated or rendered clips. Covers chaining clips into one seamless film with start and end frames, frame sequences versus scrub-ready video, pinned sections with holds for text, phone versions, loading budgets and reduced motion. Use for "scroll-driven animation", "Apple-style scroll video", "fly through the world as you sc

Instalaciones / 1h
1
GitHub Stars
443
Actualizado
9 nov
moh4696
Comunidad

threejs-scene

Builds real-time 3D websites in three.js from code alone, with no model files. Covers buildings and landmarks, vehicles, machines, landscapes and product studies made of procedural geometry (profile sweeps, lathes, instancing), canvas textures, shader patches, a physically based sky and sun, soft shadows, ambient occlusion and bloom, light presets, camera vantages and flights, quality tiers, and a starter that runs at 60 fps. Use when someone asks for a 3D website, a three.js scene, a WebGL hero

Instalaciones / 1h
1
GitHub Stars
443
Actualizado
9 nov