← 返回 Skills 市场
Core Speed Art
作者
Jiwei,Yuan
· GitHub ↗
· v1.0.1
· MIT-0
159
总下载
1
收藏
0
当前安装
6
版本数
在 OpenClaw 中安装
/install corespeed-art
功能描述
Generate video, images, audio, and music using 40+ AI models via fal.ai. Use for video generation (Kling v3, Sora 2, Veo 3.1, LTX 2.3, Pixverse v5), image ge...
使用说明 (SKILL.md)
Corespeed Art — Multi-Model AI Media via fal.ai
Auth: Set FAL_KEY with your fal.ai API key (get one at https://fal.ai/dashboard/keys).
Workflow
- Pick a model from the tables below
- Read its reference file to get the exact endpoint and parameters
- Run the command with the endpoint and JSON parameters
Usage
uv run {baseDir}/scripts/fal.py ENDPOINT --json '{"param":"value"}' -f output.ext [-i input.ext]
ENDPOINT— the fal.ai model path from the reference file (e.g.fal-ai/nano-banana-2)--json— model parameters as JSON object-f— output filename-i— input file(s) to upload (repeat for multiple), auto-injected asimage_url/image_urls/start_image_url/video_url--audio— audio input file (for lipsync)
Image Generation
| Model | Best For | Reference |
|---|---|---|
| Nano Banana 2 | Pro quality, web search, thinking | Read nanobanana.md |
| FLUX 2 Pro | Photorealistic, zero-config | Read flux.md |
| FLUX Schnell | ⚡ Fastest iteration | Read flux.md |
| FLUX Pro v1.1 | Accelerated, commercial use | Read flux.md |
| FLUX.1 Dev | 12B params, fine-tuning friendly | Read flux.md |
| GPT Image 1.5 | Transparent bg, instruction following | Read gpt.md |
| Qwen Image 2 Pro | Chinese+English, typography, native 2K | Read qwen.md |
| Recraft V4 Pro | Design/marketing, color control | Read recraft.md |
| Seedream 5 Lite | Multi-image editing, reasoning | Read seedream.md |
Video Generation
| Model | Best For | Reference |
|---|---|---|
| Kling v3 Pro I2V | Best I2V, multi-shot, audio, 3–15s | Read kling.md |
| Sora 2 T2V | Long video up to 20s, characters | Read sora.md |
| Sora 2 I2V | Image→video with Sora | Read sora.md |
| Veo 3.1 T2V | Cinematic + native audio/dialogue | Read veo.md |
| Veo 3.1 I2V | Image→video with audio | Read veo.md |
| LTX 2.3 T2V Fast | ⚡ Fast, up to 2160p/20s, open source | Read ltx.md |
| LTX 2.3 I2V | Image→video, start+end frame | Read ltx.md |
| Pixverse v5 I2V | Anime, 3D, clay, cyberpunk styles | Read pixverse.md |
Audio / TTS
| Model | Best For | Reference |
|---|---|---|
| MiniMax Speech-02 HD | 30+ languages, loudness normalization | Read minimax-speech.md |
Music & Sound Effects
| Model | Best For | Reference |
|---|---|---|
| Beatoven Music | AI music, up to 90s | Read beatoven-music.md |
Utilities
| Tool | Best For | Reference |
|---|---|---|
| Topaz Upscale | AI image/video upscale 2x–4x | Read topaz.md |
| BRIA RMBG | Professional background removal | Read bria-rmbg.md |
| Sync Lipsync | Audio-driven lip sync on video | Read sync-lipsync.md |
Notes
- No manual Python setup required. The script uses PEP 723 inline metadata.
uv runautomatically creates an isolated virtual environment and installs thefal-clientdependency on first run. - fal.ai uses a queue system — the script polls until generation completes.
- Video generation can take 30s–3min.
- Use timestamps in filenames:
yyyy-mm-dd-hh-mm-ss-name.ext. - Script prints
MEDIA:line for OpenClaw to auto-attach. - Do not read generated media back; report the saved path only.
安全使用建议
This skill appears to do exactly what it says: run a small Python client against fal.ai using your FAL_KEY. Before installing, confirm you want to give the skill access to a fal.ai API key (this allows use/billing on your account). Installing the helper 'uv' will pull packages from PyPI (uv and fal-client) — verify you trust those packages or install them in a controlled environment. Note the script will download whatever URLs the API returns and prints parts of the request JSON (your prompt may be logged to stdout); if you have sensitive prompts or inputs, avoid sending them. If you want extra assurance, review the included scripts/fal.py and the listed references (they are all present and readable) or run the script in an isolated environment first.
功能分析
Type: OpenClaw Skill
Name: corespeed-art
Version: 1.0.1
The skill bundle provides a functional wrapper for the fal.ai API to generate and edit AI media (images, video, audio). The core logic in `scripts/fal.py` uses the official `fal-client` library, handles file uploads/downloads appropriately, and follows the instructions outlined in `SKILL.md` without any evidence of data exfiltration, malicious execution, or prompt injection.
能力评估
Purpose & Capability
Name/description (multi-model fal.ai media) match the included script and reference docs. The skill requires 'uv' (used to run the included Python script) and FAL_KEY (fal.ai API key), which are reasonable and expected.
Instruction Scope
SKILL.md instructs the agent to run the provided script against fal.ai endpoints and to read the included model reference files — this is within scope. Minor privacy/operational notes: the script prints the first ~200 chars of request args (may expose prompts) and downloads whatever URLs the fal.ai API returns to disk (expected for saving outputs but could fetch arbitrary remote files if the service returns unexpected URLs).
Install Mechanism
The registry listing shows no external install spec, but SKILL.md includes an install hint to 'pip install uv'. The script uses PEP-723 inline metadata (fal-client dependency) so 'uv' will install fal-client at runtime; these are standard PyPI installs (not arbitrary archive downloads). This is moderate-risk compared with no install step but appears proportionate to the skill's needs.
Credentials
Only FAL_KEY is required. That credential is necessary for calling fal.ai and matches the described functionality. No unrelated secrets or config paths requested.
Persistence & Privilege
Skill is not always-enabled and does not request elevated platform privileges or modify other skills. Autonomous invocation is allowed (platform default) but not combined with other concerning flags.
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 corespeed-art - 安装完成后，直接呼叫该 Skill 的名称或使用
/corespeed-art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
v1.0.1
- Added pip-based installation instructions for the required uv tool.
- Removed Homebrew-specific install step for broader platform compatibility.
- Updated notes to explain that Python setup and dependencies are handled automatically via uv and PEP 723.
- No changes to core features or APIs; usage and model support remain the same.
v1.0.0
- Initial release of corespeed-art skill.
- Generate video, images, audio, and music using 40+ AI models via fal.ai.
- Supports workflows for video generation, image generation, text-to-speech, music/sound creation, upscaling, background removal, and lipsync.
- Includes model reference tables and usage instructions for each media type.
- Requires fal.ai API key (`FAL_KEY`) and uv CLI tool.
v0.0.4
- Updated authentication to require setting only the FAL_KEY environment variable for fal.ai access.
- Simplified installation instructions by removing duplicate uv install method and clarifying the required environment variable.
- Dropped support for legacy CS_FAL_GATEWAY_API_TOKEN and CS_FAL_GATEWAY_BASE_URL authentication.
- Improved metadata to explicitly require FAL_KEY in OpenClaw environments.
v0.0.3
- Image model table expanded: added FLUX Pro v1.1 and FLUX.1 Dev; removed FLUX Kontext.
- Video model table simplified: Kling O3 and some minor details removed from description.
- Description and model lists updated for improved clarity and accuracy.
- Minor language and formatting adjustments in documentation.
- No changes detected in code files.
v0.0.2
- Added an alternative shell-based installation method for the required "uv" binary (curl command for Linux/macOS).
- Updated metadata to include both Homebrew and shell install options for improved cross-platform compatibility.
v0.0.1
Initial release of multi-model AI media skill for fal.ai via uv.
- Added scripts for generating video, images, audio, and music using 40+ AI models (Kling, Sora, Veo, LTX, Pixverse, Nano Banana, FLUX, GPT Image, Qwen, Recraft, Seedream, Beatoven, Topaz, BRIA, Sync Lipsync, MiniMax, and more).
- Included reference files for all supported models with detailed usage instructions.
- Introduced a unified Python script (`fal.py`) for invoking any model via command line with consistent arguments.
- Added OpenClaw integration: prints MEDIA line for auto-attach and requires the `uv` tool.
- Removed legacy shell script.
元数据
常见问题
Core Speed Art 是什么？
Generate video, images, audio, and music using 40+ AI models via fal.ai. Use for video generation (Kling v3, Sora 2, Veo 3.1, LTX 2.3, Pixverse v5), image ge... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 159 次。
如何安装 Core Speed Art？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install corespeed-art」即可一键安装，无需额外配置。
Core Speed Art 是免费的吗？
是的，Core Speed Art 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Core Speed Art 支持哪些平台？
Core Speed Art 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 Core Speed Art？
由 Jiwei,Yuan（@jiweiyuan）开发并维护，当前版本 v1.0.1。
推荐 Skills