← 返回 Skills 市场
2159
总下载
2
收藏
7
当前安装
1
版本数
在 OpenClaw 中安装
/install runware
功能描述
Generate images and videos via Runware API. Access to FLUX, Stable Diffusion, Kling AI, and other top models. Supports text-to-image, image-to-image, upscaling, text-to-video, and image-to-video. Use when generating images, creating videos from prompts or images, upscaling images, or doing AI image transformation.
安全使用建议
This skill's code matches its description and will contact https://api.runware.ai to generate and download images/videos. However:
- The SKILL.md/scripts require a RUNWARE_API_KEY (or --api-key) but the registry metadata does not declare this; expect to supply an API key before use.
- When you pass local image file paths, the scripts will encode and upload the full image data to the Runware API — do not upload private/sensitive images unless you trust the service and its privacy/policy.
- The skill's source and homepage are listed as unknown/none in the registry; verify runware.ai and the author before trusting your API key or sensitive inputs.
- Costs: the scripts include cost reporting and the SKILL.md references pricing; ensure you understand billing on the Runware side to avoid unexpected charges.
If you are comfortable with these points (trusting the vendor, providing an API key, and not uploading sensitive files), the skill looks functionally coherent. If you need stronger assurances, ask the publisher for a verified homepage/source or confirm the Runware service and its privacy/security posture before installing.
功能分析
Type: OpenClaw Skill
Name: runware
Version: 1.0.0
The OpenClaw AgentSkills skill bundle for 'runware' is designed to interact with the Runware API for image and video generation. The `SKILL.md` provides clear, benign instructions for the AI agent and users, without any prompt injection attempts to manipulate agent behavior. The Python scripts (`scripts/image.py` and `scripts/video.py`) handle API key retrieval (from environment or argument), make legitimate API calls to `https://api.runware.ai/v1`, upload local images as data URIs, and download generated media files to the local filesystem. All observed file and network operations are directly aligned with the stated purpose of the skill, and there is no evidence of data exfiltration, malicious execution, persistence mechanisms, or obfuscation.
能力评估
Purpose & Capability
Name, description, SKILL.md, and included scripts all align: they call https://api.runware.ai/v1 to perform text->image, img2img, upscaling, text->video and img->video. The required functionality (network calls, uploading images, downloading results) is coherent with the stated purpose.
Instruction Scope
Runtime instructions and the scripts are narrowly scoped to interacting with the Runware API and reading/writing image/video files. There are no instructions to read unrelated system config, shell history, or to contact third-party endpoints outside runware.ai for control.
Install Mechanism
No install spec — code files are shipped with the skill and there are no external downloads or package installs. This minimizes install-time risk, though the included scripts will make outbound network calls at runtime.
Credentials
SKILL.md and both scripts require a Runware API key (RUNWARE_API_KEY or --api-key) but the registry metadata lists no required environment variables or primary credential — this is an inconsistency. Additionally, the scripts will read local image files and embed them as base64 in API requests (i.e., they upload the raw image content), which is expected for img2img/upscale but has privacy implications that the metadata does not call out.
Persistence & Privilege
The skill does not request permanent presence (always:false) and does not modify other skills or global agent config. It runs as-needed and only performs network I/O and local file read/write under user-invoked commands.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install runware - 安装完成后，直接呼叫该 Skill 的名称或使用
/runware触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Image and video generation via Runware API. Access to FLUX, Stable Diffusion, Kling AI, and other top models.
Features:
- Text-to-image (FLUX.1 Dev/Schnell, SDXL RealVisXL)
- Image-to-image transformation
- Image upscaling (2x/4x)
- Text-to-video (Kling AI 2.1, Runway Gen-3)
- Image-to-video animation
Includes CLI scripts with full parameter control: models, dimensions, steps, CFG, LoRA, seeds, negative prompts.
元数据
常见问题
Runware Image & Video generation 是什么？
Generate images and videos via Runware API. Access to FLUX, Stable Diffusion, Kling AI, and other top models. Supports text-to-image, image-to-image, upscaling, text-to-video, and image-to-video. Use when generating images, creating videos from prompts or images, upscaling images, or doing AI image transformation. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 2159 次。
如何安装 Runware Image & Video generation？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install runware」即可一键安装，无需额外配置。
Runware Image & Video generation 是免费的吗？
是的，Runware Image & Video generation 完全免费（开源免费），可自由下载、安装和使用。
Runware Image & Video generation 支持哪些平台？
Runware Image & Video generation 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Runware Image & Video generation？
由 26medias（@26medias）开发并维护，当前版本 v1.0.0。
推荐 Skills