← Back to Skills Marketplace
365
Downloads
0
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install video-generation-t2v-i2v
Description
AI Video generation toolkit — generate videos from text prompts or input images using multiple AI models (Veo 3.1, Veo 3, Seedance 1.5 Pro, Wan 2.5, Grok Ima...
Usage Guidance
This skill appears to do what it says: it calls the inference.sh CLI to generate video and (for image→video) uploads images to ImgBB or SM.MS. Before installing, ensure you: (1) trust the inference.sh CLI you install (install from the official source), (2) avoid uploading sensitive/private images to third-party hosts (ImgBB/SM.MS will receive the image), (3) be aware the scripts load .env from the skill folder and the current working directory (so do not keep secrets you don't want the skill process to see in .env in those locations), and (4) run in an isolated environment if you have concerns about executing external binaries or network uploads.
Capability Analysis
Type: OpenClaw Skill
Name: video-generation-t2v-i2v
Version: 1.0.1
The skill bundle requires the installation of an external third-party CLI (@inference.sh/cli) and automatically uploads local user images to public hosting services (ImgBB and SM.MS) via 'scripts/image_to_video.py'. While these actions are documented as necessary for the AI video generation process, they represent a significant privacy risk and a supply chain vulnerability by executing external binaries and exfiltrating local data to public third-party endpoints.
Capability Assessment
Purpose & Capability
Name/description (text→video, image→video) match the included Python scripts and SKILL.md. The skill depends on the external inference.sh CLI and optionally image hosting services (ImgBB/SM.MS), which is appropriate for this functionality.
Instruction Scope
Runtime instructions stay within video generation: they invoke inference.sh and (for image→video) upload images to SM.MS or ImgBB, then run the CLI and save outputs. Two minor scope notes: the scripts load .env files from the skill directory and the current working directory (which can populate environment variables), and uploaded images are transmitted to third-party hosts — both are expected for the stated features but are material to privacy.
Install Mechanism
No built-in install spec; SKILL.md instructs users to install the well-known inference.sh CLI (npm/pip) and to install Python deps via requirements.txt. No downloads from arbitrary URLs or archive extraction in the skill bundle.
Credentials
The skill does not require any platform credentials by default. It optionally uses IMGBB_API_KEY (or --api-token) to upload images to ImgBB; SM.MS can be used anonymously. The scripts read .env files (skill root and cwd) and populate environment variables, which is convenient but means local secrets in .env may be loaded into the process (the code does not exfiltrate those env vars).
Persistence & Privilege
The skill does not request persistent always-on privileges, does not modify other skills, and only writes generated video files to a local outputs directory. Autonomous invocation is allowed by default but is typical for skills and not excessive here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install video-generation-t2v-i2v - After installation, invoke the skill by name or use
/video-generation-t2v-i2v - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- Added requirement for the inference.sh CLI and provided installation instructions.
- Updated image-to-video constraints: images must be accessible via public URL, and users must supply their own API key for ImgBB or SM.MS, or use publicly accessible images.
- Clarified that for ImgBB, the API token is now required and must be provided via the `--api-token` flag or environment variable.
- Improved documentation on prerequisites and setup for both tools.
v1.0.0
- In terms of video generation, more user-friendly skills.
- Including scripts for text-to-video and image-to-video generation with clear CLI flags.
- Now supports absolute path outputs for easy UI rendering of generated videos and images.
- Example usage and available models are provided directly in the main documents.
Metadata
Frequently Asked Questions
What is Video Generation (t2v & i2v)?
AI Video generation toolkit — generate videos from text prompts or input images using multiple AI models (Veo 3.1, Veo 3, Seedance 1.5 Pro, Wan 2.5, Grok Ima... It is an AI Agent Skill for Claude Code / OpenClaw, with 365 downloads so far.
How do I install Video Generation (t2v & i2v)?
Run "/install video-generation-t2v-i2v" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Video Generation (t2v & i2v) free?
Yes, Video Generation (t2v & i2v) is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Video Generation (t2v & i2v) support?
Video Generation (t2v & i2v) is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Video Generation (t2v & i2v)?
It is built and maintained by GentleYo (@gentleyo); the current version is v1.0.1.
More Skills