IMA AI Video Generator — Short & Promo Video, Text to Video, Image to Video Generation

Name: IMA AI Video Generator — Short & Promo Video, Text to Video, Image to Video Generation
Author: allenfancy-gan

作者 allenfancy-gan · GitHub ↗ · v1.0.13 · MIT-0

cross-platform ✓ 安全检测通过

820

总下载

当前安装

版本数

在 OpenClaw 中安装

/install ima-video-ai

功能描述

AI video generator with premier models: Wan 2.6, Kling O1/2.6, Google Veo 3.1, Sora 2 Pro, Pixverse V5.5, Hailuo 2.0/2.3, SeeDance 1.5 Pro, Vidu Q2. Video ge...

使用说明 (SKILL.md)

IMA Video AI

When To Use

Use this repository for text-to-video, image-to-video, reference-image video generation, and first/last-frame interpolation. This repo is video-only; do not route image editing, audio, or non-video tasks here.

Quick Start

Get your API key at https://www.imaclaw.ai/imaclaw/apikey, then export it: export IMA_API_KEY="your-api-key"
Run a low-cost health probe before spending credits: python3 scripts/ima_runtime_doctor.py --task-type text_to_video
First-time setup: python3 scripts/ima_runtime_setup.py
Manual first-run alternative if you skip setup: in an interactive terminal, python3 scripts/ima_runtime_cli.py --task-type text_to_video --prompt "..." now prompts for a suggested model; non-interactive callers should still use --model-id or --list-models
Natural-language wrapper: python3 scripts/route_and_execute.py --request "做一个 10 秒的产品视频" for parse + validate + execute

First-Run Rules

Runtime model resolution is fixed: --model-id -> saved preference -> interactive TTY prompt -> fail; there is no hidden default model.
First use can run python3 scripts/ima_runtime_setup.py, accept the first-run CLI prompt in a terminal, or choose --model-id after --list-models; setup writes only ~/.openclaw/memory/ima_prefs.json, never IMA_API_KEY.
Install Python dependencies with pip install -r requirements.txt; Pillow is used for image-dimension probing.
Ensure ffprobe is on PATH for video/audio metadata probing and ffmpeg is on PATH for derived video cover extraction.

Picks And Errors

Start with ima-pro-fast for text_to_video / image_to_video; start with kling-video-o1 for reference_image_to_video / first_last_frame_to_video. Full matrix: references/shared/model-selection-policy.md
401 or invalid key -> regenerate at https://www.imaclaw.ai/imaclaw/apikey and rerun ima_runtime_doctor.py; 403 / 4014 -> subscribe or switch to ima-pro-fast; 6009 / 6010 -> remove custom params and confirm the live catalog with --list-models

Video Modes

first_last_frame means explicit start/end frames with generated motion between them; reference means style or character guidance, not literal frame 1.

Gateway Contract

Treat this file as the public gateway, not the full rulebook.

The generation entrypoint is python3 scripts/ima_runtime_cli.py ....
python3 scripts/route_and_execute.py is the natural-language wrapper over the structured runtime.
python3 scripts/ima_runtime_setup.py and python3 scripts/ima_runtime_doctor.py are onboarding helpers, not alternate generation runtimes.
No other generation CLI path is part of the active runtime contract.
Remote HTTPS reference media must be direct public URLs. The runtime may temporarily download them locally for metadata probing, Seedance preflight checks, and video-cover extraction; private/internal hosts, credentialed URLs, redirects, and oversized downloads are rejected.
Local media files and derived video cover frames use IMA's upload-token flow and then upload to the pre-signed HTTPS storage URL returned by that service.
Build a GatewayRequest for a video target.
Resolve task type before execution, and clarify when image roles are ambiguous.
Query the product list before task creation so attribute_id, model_version, and defaults come from the live catalog.
Return video results as remote HTTPS URLs; do not convert them into local file attachments.

Read Order

references/README.md, references/gateway/entry-and-routing.md, references/gateway/workflow-confirmation.md, references/shared/model-selection-policy.md, references/shared/error-policy.md, references/shared/security-and-network.md, capabilities/video/CAPABILITY.md

Boundary

references/gateway/* covers entry/routing, references/shared/* covers shared runtime policy, capabilities/video/* owns video behavior, and _meta.json plus clawhub.json remain metadata inputs.

安全使用建议

This package appears to do what it claims, but review these practical points before installing or running it: 1) The skill uploads any local files you pass to the provider (it uses an upload-token + pre-signed PUT flow). Do not pass sensitive local files—only give media you intend to upload. 2) It requires and will send IMA_API_KEY to the provider endpoints; use a scoped or test key for initial trials. 3) Logs and a small prefs file are written under ~/.openclaw/ (logs retained ~7 days). If you need absolute assurance about handling of downloaded remote media, or about rejection of redirects/credentialed URLs, inspect the networking code (shared/client.py and references/shared/security-and-network.md) before use. 4) There are minor metadata mismatches (homepage/branding variations in files), which are not directly dangerous but you may want to confirm you trust the provider domain (https://www.imaclaw.ai and api.imastudio.com) before giving the API key.

功能分析

Type: OpenClaw Skill Name: ima-video-ai Version: 1.0.13 The IMA AI Video Generator skill bundle is a well-structured and transparent implementation for interfacing with the IMA Studio video generation API. It includes comprehensive logic for task routing, model selection, and media processing using ffmpeg/ffprobe. While it requires an API key and performs network requests to api.imastudio.com and imapi.liveme.com (for media uploads), these behaviors are explicitly disclosed in SKILL.md, clawhub.json, and SECURITY.md. The code also includes security-conscious features such as SSRF protection in media_utils.py (validating public IP addresses for remote downloads) and uses safe subprocess execution patterns. No evidence of malicious intent, data exfiltration, or unauthorized persistence was found.

能力标签

requires-oauth-token

能力评估

✓ Purpose & Capability

Name/description match the code and runtime contract: the skill requires a single provider API key (IMA_API_KEY), Python + ffmpeg/ffprobe, and uses requests/Pillow for network and image probing. Those requirements are proportional to a video-generation connector that uploads local media and polls remote tasks.

ℹ Instruction Scope

SKILL.md and the CLI/scripts clearly instruct the agent to accept prompts, probe remote or local media, and (for local files) obtain an upload-token then PUT bytes to a pre-signed HTTPS storage URL. This is expected for media uploads, but it means the tool will read and transmit any local files you provide. SKILL.md claims only direct public HTTPS remote media are allowed and that temp downloads are deleted; those policies appear documented in the repo, but you should review the implementation if you need strict guarantees.

✓ Install Mechanism

No download-from-URL install is present; the repo is instruction/code-based and uses a typical requirements.txt (requests, Pillow). No installer pulls arbitrary archives or executes code from unknown hosts. Installing Python deps (pip install -r requirements.txt) is the only setup friction called out.

✓ Credentials

Only one environment secret is required: IMA_API_KEY (declared as primary). That is appropriate for a single-provider API integration. The scripts read IMA_API_KEY (or accept --api-key) and do not request other unrelated credentials or system secrets in the visible files.

ℹ Persistence & Privilege

The skill writes preferences and logs to ~/.openclaw/memory/ima_prefs.json and ~/.openclaw/logs/ima_skills/. Log retention is documented (7 days). The skill is not marked always:true and does not modify other skills' configs. Be aware that logs may contain operational information (e.g., model choices, errors); they are stored on disk by default.

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 ima-video-ai
安装完成后，直接呼叫该 Skill 的名称或使用 /ima-video-ai 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

v1.0.13

- Removed the sample end-to-end smoke playbook (references/operations/e2e-smoke-playbook.md). - Updated documentation to remove knowledge base integration and guidance details from SKILL.md. - No runtime or API changes; impact is limited to documentation and reference cleanup.

v1.0.12

Major refactor: modularized video capability, added references, improved setup/requirements, and clarified runtime flow. - Modularized the skill: new capabilities/video packages and structured references/ documentation added. - Video generation runtime now supports a clear entrypoint (`ima_runtime_cli.py`) and a natural-language gateway wrapper. - Added onboarding and setup helpers (`ima_runtime_setup.py`, `ima_runtime_doctor.py`). - Requirements updated: Pillow, ffmpeg, and ffprobe now required for image/video probing and cover extraction. - Documentation separated: all key API, workflow, parameters, errors, and selection rules moved to reference files. - Old monolithic scripts and detail docs removed; migration to a strict gateway/contract approach.

v1.0.11

- Skill renamed to "IMA AI Video Generator" for clarity. - Expanded keywords and description to emphasize short video, promo video, and marketing content use cases. - Added references to new/improved models: Pixverse V5.5, clarified support for SeeDance 1.5 Pro, Vidu Q2, Hailuo 2.0/2.3. - Updated homepage link in metadata to https://www.imaclaw.ai. - Emphasized AI video generation modes (text-to-video, image-to-video, first-last-frame, reference-image) and character consistency features. - Positioning clarified as an alternative to standalone skills and popular tools like Runway, Pika Labs, and Luma.

v1.0.10

- Updated keywords to improve searchability, adding terms like "AI video generator" and "short video generator". - No functional or API changes; all flows and usage unchanged. - Minor metadata improvements for discoverability. - Documentation updated for better keyword coverage; no core feature changes.

v1.0.9

**v1.1.0 changelog** - Added detailed technical/API documentation in new SKILL-DETAIL.md file. - Included !keywords.txt for improved keyword and capability indexing. - Refactored and clarified SKILL.md: model ID reference table, task_type logic, error handling, user preference memory, and usage examples are more concise. - Expanded coverage in documentation for new and popular models (Hailuo, SeeDance, Vidu). - Improved instructions for model selection, polling, and user-facing protocol. - Security, error, and user experience FAQ now referenced in SKILL-DETAIL.md.

v1.0.8

- Added full standalone mode: ima-video-ai now runs independently; ima-knowledge-ai integration is optional. - Updated guidance: Reading the knowledge base is recommended but not mandatory. - Clarified instructionScope and persistence; explained credentials, logs, and preference retention. - Improved documentation to highlight standalone use and optional cross-skill enhancement for visual consistency.

v1.0.7

# ima-video-ai 1.0.7 Changelog - Added Ima Sevio 1.0 / 1.0-Fast (IMA Video Pro / Pro Fast) to supported model list and documentation. - Expanded and updated model lookup tables with new model aliases and corrected model_id mappings. - Enhanced SKILL.md with clearer instructions, use cases, and improved model reference tables. - Added SECURITY.md file for improved security and compliance guidance. - Internal script and metadata updates for model recognition and input parsing.

v1.0.6

Version 1.0.6 – Changelog - Added new file: clawhub.json for integration/metadata purposes. - No changes to core logic or functionality. - Documentation and supported model information remain unchanged.

v1.0.5

- No code or functionality changes in this release. - Expanded keywords in metadata to improve discoverability (now includes Chinese terms and popular model names). - Version in SKILL.md remains at 1.0.8; no other documentation updates made.

v1.0.3

IMA Studio Video Generation (ima-video-ai) v1.0.3 → v1.0.8 - Major update: SKILL documentation now includes comprehensive input parsing guides for agents/models, greatly improving usability and user intent recognition. - All standalone Markdown docs (INSTALL.md, README.md, SECURITY.md, and previous changelog) were removed for a streamlined package. - Added _meta.json for improved skill metadata handling/integration. - Guidance expanded: More explicit mapping between user inputs and task_type/model parameters, including normalization tables for phrasing/model/duration/resolution. - Clearer recommendations for handling multi-shot/character consistency, with fallback instructions if ima-knowledge-ai is not installed. - Description updated to emphasize multi-model support, practical use-cases, and why to use this over similar skills or direct API integration.

v1.0.2

## ima-video-ai 1.0.3 Changelog - Added a mandatory pre-check section, requiring all users to consult the ima-knowledge-ai knowledge base (especially visual-consistency.md and video-modes.md) before generating videos. - Clarified the difference between image_to_video and reference_image_to_video modes, with examples and workflow guidance. - Updated usage instructions with strict requirements to ensure correct visual consistency and reference handling. - Emphasized that skipping the knowledge base check is a bug and provided workflow pseudocode for proper mode selection. - Previous privacy/security, model selection, and technical details remain unchanged.

v1.0.1

Version 1.0.2 - Added explicit documentation about usage of two IMA Studio domains (`api.imastudio.com` and `imapi.liveme.com`) for API and image file uploads. - Updated security and privacy sections to clarify that your API key may be sent to both domains, with image uploads going through `imapi.liveme.com` for certain tasks. - Provided best practices and verification steps for users concerned about multi-domain credential exposure. - No code changes; documentation only.

v1.0.0

IMA Studio Video Generation 1.0.1 — Adds detailed documentation, default model rules, and enhanced privacy transparency. - Added comprehensive SKILL.md with usage instructions, privacy details, and sample usage for all supported video generation modes. - Specified default model selection rules: always recommend the newest and most popular models by default. - Outlined strict content safety for Sora 2 Pro, with prompt dos and don'ts. - Detailed security and privacy policy: what data is sent, stored locally, and user controls for logs/preferences. - Provided clear user guidance on how video URLs should be sent for best experience in messaging platforms.

元数据

Slug ima-video-ai

版本 1.0.13

许可证 MIT-0

累计安装 2

当前安装数 2

历史版本数 13

常见问题