Wan 2.6 Flash Reference Image to Video
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md to install @user_f95f21b8/dlazy-wan2-6-r2v-flash.
About this skill
Problem
When engineers already have reference images but need quickly previewable dynamic short videos, manually calling a cloud API, handling auth, uploading assets, and polling tasks can become repetitive and brittle. This skill wraps the Wan 2.6 Flash reference-image-to-video capability as a CLI client, suitable for scripts, agent workflows, or local tooling.
How It Works
The skill does not implement model inference; it is a thin client for the dLazy hosted API:
- Authentication: requires a dLazy API key, configured via CLI or supplied through DLAZY_API_KEY.
- Generation: sends prompts, parameters, and reference image paths to dLazy; local files are uploaded to dLazy media storage for model access.
- Output: returned media URLs are hosted by dLazy's file service.
- Async mode: non-waiting invocations return outputs: [] and a task status object, which can be polled until completion.
- Error handling: distinguishes auth failures, missing parameters, missing local files, insufficient balance, and backend errors for cleaner retries or user guidance.
Limits
It is best for quick reference-to-video prototypes and batch calls, not local offline inference. Use requires a dLazy account and valid API key; assets are processed in the cloud, so sensitive content must follow the service terms. If the response indicates insufficient balance or invalid auth, guide the user to recharge or reconfigure the key instead of blindly retrying.
Use Cases
- Turn product reference images into short preview videos to send to clients for feedback.
- Batch convert concept images into dynamic clips via script and poll async tasks until done.
- Generate video URLs from prompts and reference images inside an agent workflow for editing.
- Evaluate Wan 2.6 Flash image-to-video output while handling auth and balance errors.
Best For
- Video editors who need quick short video drafts from reference images.
- Workflow engineers calling image-to-video APIs and polling async tasks in agents.
- Product operators generating dynamic preview assets for product pages.
- Toolchain engineers debugging dLazy CLI auth, balance, and error codes.
Related Skills
Generate an interactive HTML product detail page from images and copy, with multi-product carousel, inline text editing, design controls, and PDF/JPG/PSD export support.
Enter a material name to get preview and download links for free, commercially usable video assets, with paid platform options, pricing, and search suggestions when results are limited.
A local CLI for Dreamina image and video generation, including credit checks, async submission, result queries, and task history review.
An AI-guided workflow for Chinese video dubbing and subtitles that configures iFlytek or edge-tts, splits audio, generates SRT, and composes the final video.