← 返回 Skills 市场

corespeed-studio

Name: corespeed-studio
Author: zypher-agent

作者 Zypher Agent · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ 安全检测通过

147

总下载

当前安装

版本数

在 OpenClaw 中安装

/install corespeed-studio

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 as image_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 run automatically creates an isolated virtual environment and installs the fal-client dependency 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.

Support

Built by Corespeed. If you need help or run into issues:

💬 Discord: discord.gg/mAfhakVRnJ
🐦 X/Twitter: @CoreSpeed_io
🐙 GitHub: github.com/corespeed-io/skills

安全使用建议

This skill appears to do what it says: it will use your FAL_KEY to call fal.ai, upload any local input files you pass, and download generated media to disk. Before installing or running it, ensure you: (1) only provide a fal.ai API key you control and understand the billing/permissions tied to it; (2) avoid uploading sensitive local files (they will be transmitted to fal.ai); (3) review the 'uv' package provenance before pip-installing it or run the script inside an isolated environment; (4) be aware the script will fetch output URLs and save them locally (network fetches could reach external hosts returned by fal.ai); and (5) monitor your fal.ai usage to avoid unexpected costs. If you need stronger guarantees, request that the skill author provide a signed package or host the runner in a sandboxed environment.

功能分析

Type: OpenClaw Skill Name: corespeed-studio Version: 1.0.0 The skill bundle provides a comprehensive and well-structured interface for generating AI media (images, video, audio) via the fal.ai API. The core logic in `scripts/fal.py` uses the official `fal-client` library to handle file uploads, poll for results, and download generated media to the local system. The documentation in `SKILL.md` and the `references/` directory is extensive, providing clear schemas and examples for over 40 models. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found; the script's behavior is entirely consistent with its stated purpose.

能力评估

✓ Purpose & Capability

Name/description (multi-model media via fal.ai) matches requirements and artifacts: the script calls fal_client, needs FAL_KEY, and the SKILL.md lists many fal.ai model endpoints. Requesting the 'uv' runner and FAL_KEY is appropriate for this functionality.

ℹ Instruction Scope

The SKILL.md and script restrict actions to interacting with fal.ai. The script uploads any local input files (via fal_client.upload_file) and downloads output URLs (urllib.request.urlretrieve). These are expected for a media generation tool, but users should note that local files are transmitted to fal.ai and output URLs are fetched from the network and saved to disk; the script also prints 'MEDIA:' lines for automatic attachment.

✓ Install Mechanism

No registry install spec; the skill is instruction-only with one script file. SKILL.md includes an optional install step (pip install uv). That is a normal package installation method (uv is a known runner). There are no downloads from untrusted hosts or extract/install of arbitrary archives in the repository.

✓ Credentials

Only FAL_KEY is required and used. No additional unrelated secrets/config paths are requested. The script checks only FAL_KEY and does not read other environment variables or system credentials.

✓ Persistence & Privilege

always is false and the skill does not attempt to modify other skills or system-wide agent configuration. It writes generated media to disk (expected behavior) but does not persist credentials or enable itself automatically.

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-studio
安装完成后，直接呼叫该 Skill 的名称或使用 /corespeed-studio 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

Initial release of corespeed-studio — multi-model AI media generator via fal.ai. - Supports video, image, audio, and music generation using 40+ fal.ai models. - Easy command-line workflow with isolated environment and automatic dependency setup. - Includes video generation (Kling, Sora, Veo, LTX, Pixverse), image generation (Nano Banana, FLUX, GPT Image, Recraft), text-to-speech, AI music, upscaling, background removal, and lipsync. - Tables describe best use per model and link to reference files for parameters. - No manual Python setup required; outputs ready-to-use media files.

元数据

Slug corespeed-studio

版本 1.0.0

许可证 MIT-0

累计安装 1

当前安装数 1

历史版本数 1

常见问题