model-selector
Model-selector guides you through choosing the right AI video generator from a curated set of 16 commercial and open-source options. It asks targeted questions about your project's needs—duration, audio, language, editing requirements, deployment constraints—then recommends the 1–3 models that match best, with clear explanations of why each fits.
Model-selector helps you pick the best AI video model for your specific project by matching your requirements against 16 leading options.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-06-01
Model-selector helps you pick the best AI video model for your specific project by matching your requirements against 16 leading options. Model-selector guides you through choosing the right AI video generator from a curated set of 16 commercial and open-source options. It asks targeted questions about your project's needs—duration, audio, language, editing requirements, deployment constraints—then recommends the 1–3 models that match best, with clear explanations of why each fits.
Use it when
- Model-selector compares video generation models across key dimensions: output quality, character consistency, physics simulation.
- Yes.
Verify before relying
Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.
Install
cclank/lanshu-awesome-ai-video-kit/model-selector · repository language: HTML
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
Which AI video model should I use for my project?
Model-selector helps you find the right fit by asking about your specific needs—video length, audio requirements, language support, editing capabilities, and deployment preferences. Based on your answers, it recommends 1–3 models from its curated set of 16 commercial and open-source options, explaining why each matches your use case.
How does model-selector compare multiple video generation models?
Model-selector compares video generation models across key dimensions: output quality, character consistency, physics simulation, audio integration, language support (including Chinese), editing capabilities, and deployment options. It narrows the full set down to your best 1–3 matches based on your project's constraints and goals.
Can I find free or open-source video generation options?
Yes. Model-selector includes open-source and free-tier models alongside commercial options in its curated set of 16. It can filter for locally deployable, open-source solutions if you specify that constraint, helping you avoid vendor lock-in or licensing costs.
What video model supports Chinese or local deployment?
Model-selector identifies models with Chinese language support and local deployment capabilities when you indicate those requirements. It covers both domestic Chinese platforms and international models with native Chinese support, plus open-source options suitable for on-premise or self-hosted deployment.
Can model-selector help with video editing or enhancement?
Model-selector assesses each model's editing and enhancement capabilities—such as inpainting, style transfer, lip-sync, and frame interpolation—and recommends models that excel at those tasks if editing is part of your workflow. It distinguishes between pure generation and editing-focused tools.
How does model-selector guide my choice for short-form or movie-quality content?
Model-selector asks about your target format and quality bar, then recommends models optimized for that use case. For short-form content, it may suggest faster, lower-cost models; for movie-quality output, it prioritizes physics simulation, character consistency, and native audio support.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
model-selector
15 个主流 AI 视频模型(11 商业 + 4 开源)的"购物顾问"。问用户 3-4 个关键问题,给出推荐 + 理由。
何时不用此 skill
- 用户已经确定要用某个模型 → 用对应的
<model>-prompterskill - 用户问"提示词怎么写" → 用
seedance-prompter/kling-prompter/happyhorse-prompter - 用户的提示词不工作 → 用
seedance-debugger
11 模型能力速查矩阵
| 模型 | 中文 | 音频 | 物理 | 编辑 | 时长 | 开源 | 国内可用 | 主战场 |
|---|---|---|---|---|---|---|---|---|
| Seedance 2.0 | ★★★ | — | ★★★ | — | 15s | — | ✓ | 电影叙事 |
| HappyHorse 1.0 | ★★★ | ★★ | ★★ | — | 15s（默认 5s） | — | ✓ | ASMR / 短片 |
| Kling 3.0 | ★★★★★ | ★★★★ | ★★★★ | ✓ | 2m | — | ✓ | 中文剧情 / 图生视频 |
| Sora 2 | ★★ | ★★★★ | ★★★★★ | — | 25s (Pro) | — | △ | 电影艺术片 |
| Veo 3.1 | ★★ | ★★★★★ | ★★★ | — | 148s chained | — | △ | 多人对话 |
| Gemini Omni ⭐NEW | ★★ | ★★★ |
(truncated - see the full file via the links below)
File tree — 1 file
skills/model-selector/SKILL.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Find the best AI video model for a specific use case”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Prompt Translator converts video prompts across models by matching your input to one of 10 reference scenarios, then applying the target model's format rules from a lookup table of 110 cross-model examples. It preserves all semantic content while restructuring labels and phrasing to fit each model's official formula.
Higgsfield Video routes your requests to 11 official AI video models—including Sora 2, Google Veo 3, Kling variants, Seedance Pro, and Cinema Studio 3.5—automatically selecting the best fit for your use case. It supports text-to-video and image-to-video workflows, applies 6 video presets (UGC, Unboxing, Product review, Hyper motion, TV spot, Wild Card), handles character consistency with Kling Avatars 2.0, and manages async job polling until your video is ready.
Create videos directly from text descriptions by routing requests through your choice of four API gateways. Supports seven major video generation models—Seedance 2.0, Kling, VEO, Sora, Runway, MiniMax, and Gemini Omni—with automatic provider selection, cost comparison, and fallback handling. Gemini Omni adds stateful editing for refining existing clips.
Higgsfield Operator teaches you to generate cinematic AI videos using Higgsfield's unified platform, which combines Sora 2, Veo 3.1, WAN 2.5, Kling 2.6, and other models with professional controls like camera simulation and character consistency. Learn image-to-video workflows, VFX application, talking-head creation, and Python SDK automation across 70+ camera presets and 23+ effects.
Create short videos from text descriptions or still images by routing to your choice of 10 providers—OpenAI Sora, Google Veo, Runway, Pika, Luma, and others—all through a single command-line interface. Supports text-to-video, image-to-video, and optional last-frame control where available, with configurable duration, aspect ratio, and resolution.
Access fal.ai's complete text-to-video generation system with support for multiple models including Kling 2.6 Pro, Sora 2, LTX-2 Pro, Runway Gen-3 Turbo, and Luma Dream Machine. Configure video duration, aspect ratio, and motion prompts to generate cinematic content with optional native audio. Use quality-focused models for final output or fast-iteration options for previews.
More skills Eachlabs Video Generation (unlicensed) · Math Modeling Solver (unlicensed)