How do I install the Uni Vision Engine skill?

Run npx skillmds@latest add dvcrn/uni-vision-engine in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Uni Vision Engine safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: executes scripts. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Uni Vision Engine?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Uni Vision Engine free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Uni Vision Engine?

dvcrn (@dvcrn) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Uni Vision Engine by dvcrn — Agent Skill

Name: Uni Vision Engine
Rating: 4.2 (5 reviews)
Author: dvcrn

Uni Vision Engine

Automated high-quality video generation (text-to-video, image-to-video) via a local jimeng-api Docker service. Features native OpenClaw image interception, allowing users to send images directly in chat to generate videos without any UI.

dvcrn Updated Sep 8, 2026 32 repo stars

File contents

Uni Vision Engine (v1.2.0)

This skill leverages a local jimeng-api Docker service. It allows AI agents to fully control high-quality image-to-video and text-to-video generation using a valid sessionid.

🌟 Core Feature: Native Chat Image Interception (Best Practice)

With this skill, the AI Assistant can automatically intercept clothing/character images sent by the user in the chat interface and seamlessly pass them to the generation model—no manual web uploads required!

Content Moderation Warning (China Firewall)

Note: Because this relies on the domestic Jimeng/Seedance engine, there is strict automated content moderation for clothing. If you encounter error -2001 (First frame image upload failed: may contain violating content), this means the image is deemed "too revealing", shows too much skin, or contains sensitive elements. The firewall outright blocks these. No credits are deducted. If this occurs, ask the user to provide a different image or switch to an overseas engine like Luma/Runway.

CLI Usage (For Automation Scripts)

1. Text-to-Video

node {baseDir}/scripts/generate.js --prompt "A Shiba Inu surfing" --session "your_sessionid"

2. Image-to-Video (Requires --image)

node {baseDir}/scripts/generate.js --prompt "Model turning naturally to show outfit" --image "/tmp/target.jpg" --session "your_sessionid"

Notes:

Requires sufficient credits in the Jimeng account.

Using jimeng-video-3.0-pro deducts 50 credits per run.

---name: uni-vision-enginedescription: Automated high-quality video generation (text-to-video, image-to-video) via a local jimeng-api Docker service. Features native OpenClaw image interception, allowing users to send images directly in chat to generate videos without any UI.---# Uni Vision Engine (v1.2.0)This skill leverages a local `jimeng-api` Docker service. It allows AI agents to fully control high-quality image-to-video and text-to-video generation using a valid `sessionid`.## 🌟 Core Feature: Native Chat Image Interception (Best Practice)With this skill, the AI Assistant can **automatically intercept** clothing/character images sent by the user in the chat interface and seamlessly pass them to the generation model—**no manual web uploads required!**<agent_instruction>When a user sends a "character/outfit" photo in the chat and intends to animate it (e.g., showing off the clothing, turning around), you MUST execute the following steps:1. **Intercept the Image Payload**: Use the `read` tool or native execution flow to extract the base64 content or cache path of this image from the chat context. Save it as a local temporary file (e.g., `/tmp/target.jpg`).2. **Never use text-based URLs or JSON format for image uploads**. You MUST use Node.js `multipart/form-data` to submit the physical file stream.3. **Initiate the Video Generation Task using the core script**:```bashnode {baseDir}/scripts/generate.js --prompt "The model naturally turns around, fully showcasing the gloss of the fabric, extremely high quality, natural sunlight..." --image /tmp/target.jpg```4. **Monitor the Output**: Generation usually takes 60-310 seconds. Monitor the Docker logs to retrieve the direct MP4 link and return it to the user.</agent_instruction>## Content Moderation Warning (China Firewall)**Note**: Because this relies on the domestic Jimeng/Seedance engine, there is strict automated content moderation for clothing. If you encounter error `-2001` (First frame image upload failed: may contain violating content), this means the image is deemed "too revealing", shows too much skin, or contains sensitive elements. The firewall outright blocks these. No credits are deducted. If this occurs, ask the user to provide a different image or switch to an overseas engine like Luma/Runway.## CLI Usage (For Automation Scripts)### 1. Text-to-Video```bashnode {baseDir}/scripts/generate.js --prompt "A Shiba Inu surfing" --session "your_sessionid"```### 2. Image-to-Video (Requires --image)```bashnode {baseDir}/scripts/generate.js --prompt "Model turning naturally to show outfit" --image "/tmp/target.jpg" --session "your_sessionid"```> **Notes:**> 1. Requires sufficient credits in the Jimeng account.> 2. Using `jimeng-video-3.0-pro` deducts **50 credits** per run.

Frequently asked questions