CapCut Video Generation Alternative
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md to install @infimind/capcut-video-generation-alternative.
About this skill
Problem
Video generation APIs often require understanding mode, media fields, taskId polling, and upload flows. Creators, operators, or teams producing ads, e-commerce, or short-drama assets may switch between platforms, retry prompts, and wait for results. This Skill narrows that workflow to a single submission: provide a prompt, optionally add images, video, or audio, and receive an MP4/MOV file.
How It Works
It wraps AI Hive OpenAPI Seedance video capabilities and maps modes to fixed publicModelId values:
- Text to video:
t2vfor generating concepts from prompts - Image to video:
i2vusing first or last frame control - Reference to video:
r2vwith reference images, video, or audio - Edit / extend:
editandextendfor reworking or lengthening existing media
The key steps are querying live models and pricing, defaulting to COST_FIRST, validating inputs, submitting and returning taskId, polling that task, and downloading to ~/Downloads/AiHive. Prompts should follow “subject and scene → action order → camera motion → lighting → sound → constraints → output specs” to avoid conflicting subject and camera actions.
Boundaries
It is suitable for content creation, TVC, e-commerce product display, short videos, and serialized content, but it is not an official interface for any competitor and does not guarantee compliance with third-party platform sizes, advertising, or product policies. A local timeout does not mean failure; keep the taskId and query instead of resubmitting. Models, parameters, pricing, and media limits are determined by live runtime configuration.
Use Cases
- Produce a 15-second product demo for a detail page, emphasizing structure, material, and use case.
- Rework a live-stream clip into a Douyin sales ad while controlling people, product, and actions.
- Generate AI short-drama or anime-drama shots using character sheets, scene references, and script beats.
- Submit reference images and voiceover audio for a product video, then track and download via taskId.
Best For
- E-commerce visual designers: need batch product hero videos and detail-page demos.
- Short-drama writers or directors: need consistent characters, outfits, and style across shots.
- Paid-media buyers: need quick feed-ad versions from scripts and reference assets.
- Content creators: want prompt, image, or audio inputs turned into downloadable videos.
Related Skills
Excalidraw Wrap is an Excalidraw-focused wrapper, with tags for TypeScript, GitHub, and automation.
Calibrate vague brand inputs, expose contradictions, distill a brand core and positioning boundaries, then stress-test the result into an executable brand skeleton.
Generate localized Chinese brand names, naming directions, slogans, and risk checklists with reusable templates and trademark search reminders.
A beginner-friendly photo analysis tool that infers shooting parameters from visual features and suggests post-processing, optimization, and learning keywords.