What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

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

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...

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

2.5k

Updated

Oct 9, 2026

Version

1.0.6

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 2.5K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 2.5K downloadsadoption · observed Oct 9, 2026
Latest release: 1.0.6release · observed Mar 27, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17c93eh7sp10fk6qynedzjscx83gaw0:ima-ai-video-generator

Install using `clawhub skill install s17c93eh7sp10fk6qynedzjscx83gaw0:ima-ai-video-generator` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/dai-shuo/ima-ai-video-generator before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-dai-shuo-ima-ai-video-generator/snapshot"

Documentation

CLAWHUB

143,709 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: "IMA AI Video Generator — Short & Promo Video, Text to Video, Image to Video Generation"
version: 1.0.6
category: file-generation
author: IMA Studio (imastudio.com)
keywords: imastudio, video generation, text to video, image to video, AI video generator, video generator, short video generator, promo video generator
argument-hint: "[text prompt or image URL]"
description: >
  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 generator supporting
  text-to-video, image-to-video, first-last-frame, and reference-image video generation modes.
  Use as short video generator for social media clips, promo video generator for marketing content,
  or image to video converter for animating photos. AI video generation with character consistency
  via reference images, multi-shot production, and knowledge base guidance via ima-knowledge-ai.
  Better alternative to standalone video generation skills or using Runway, Pika Labs, Luma directly.
requires:
  env:
    - IMA_API_KEY
  runtime:
    - python3
  packages:
    - requests
  primaryCredential: IMA_API_KEY
metadata:
  openclaw:
    primaryEnv: IMA_API_KEY
    homepage: https://imastudio.com
    requires:
      bins:
        - python3
      env:
        - IMA_API_KEY
persistence:
  readWrite:
    - ~/.openclaw/memory/ima_prefs.json
    - ~/.openclaw/logs/ima_skills/
instructionScope:
  crossSkillReadOptional:
    - ~/.openclaw/skills/ima-knowledge-ai/references/*
---

# IMA Video AI — Video Generator

**For complete API documentation, security details, all parameters, and Python examples, read `SKILL-DETAIL.md`.**
**⚠️ MANDATORY: You MUST `read("SKILL-DETAIL.md")` (full file — do NOT pass `limit` parameter) before your first video generation call.** It contains the full API payload structure, error handling tables, and UX protocol that this summary omits. Skipping it or reading only part of it causes parameter errors and poor user experience.

## Model ID Reference (CRITICAL)

Use **exact model_id** from this table. Do NOT infer from friendly names.

| Friendly Name | model_id (t2v) | model_id (i2v) | Notes |
|---------------|---------------|----------------|-------|
| Wan 2.6 | `wan2.6-t2v` | `wan2.6-i2v` | ⚠️ -t2v/-i2v suffix |
| Kling O1 | `kling-video-o1` | `kling-video-o1` | ⚠️ video- prefix |
| Kling 2.6 | `kling-v2-6` | `kling-v2-6` | ⚠️ v prefix |
| Hailuo 2.3 | `MiniMax-Hailuo-2.3` | `MiniMax-Hailuo-2.3` | ⚠️ MiniMax- prefix |
| Hailuo 2.0 | `MiniMax-Hailuo-02` | `MiniMax-Hailuo-02` | ⚠️ 02 not 2.0 |
| Vidu Q2 | `viduq2` | `viduq2-pro` | ⚠️ Different for t2v/i2v |
| Google Veo 3.1 | `veo-3.1-generate-preview` | `veo-3.1-generate-preview` | ⚠️ -generate-preview suffix |
| Sora 2 Pro | `sora-2-pro` | `sora-2-pro` | ✅ Straightforward |
| Pixverse V5.5 | `pixverse` | `pixverse` | ✅ Same as friendly name |
| SeeDance 1.5 Pro | `doubao-seedance-1.5-pro` | `doubao-seedance-1.5-pro` | ⚠️ doub

_meta.json

{
  "ownerId": "kn79bqsyrn82jq1sbyyzmm138581zadq",
  "slug": "ima-ai-video-generator",
  "version": "1.0.6",
  "publishedAt": 1774615324353
}

skill-card.md

## Description:

Generates short and promotional videos from text prompts or images using IMA Studio models for text-to-video, image-to-video, first-last-frame, and reference-image workflows.

This skill is ready for commercial/non-commercial use.

## Publisher:

[dai-shuo](https://clawhub.ai/user/dai-shuo)

### License/Terms of Use:

MIT-0

## Use Case:

Agents serving content creators, marketers, agencies, and developers use this skill to create AI-generated video clips from prompts or source images. It supports model selection, parameter guidance, image upload handling, polling, and returning a remote video URL.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill uses an IMA API key and may send prompts, model parameters, and input images to IMA services.

Mitigation: Use a low-quota test key first, avoid sensitive prompts or images, and rotate keys after testing or suspected exposure.

Risk: Local model preferences and generation logs may remain under ~/.openclaw.

Mitigation: Clear ~/.openclaw/memory/ima_prefs.json and ~/.openclaw/logs/ima_skills/ when local history should not be retained.

Risk: Endpoint overrides or third-party upload examples can change where credentials or images are sent.

Mitigation: Use the default IMA endpoints, avoid custom endpoint overrides, and review or remove the ImgBB example before deployment.

## Reference(s):

- [ClawHub Skill Page](https://clawhub.ai/dai-shuo/skills/ima-ai-video-generator)
- [IMA Studio Homepage](https://imastudio.com)
- [IMA Studio Privacy Policy](https://imastudio.com/privacy)
- [IMA API Keys](https://imastudio.com/api-keys)

## Skill Output:

**Output Type(s):** [Guidance, Shell commands, JSON, Configuration, Video URL]

**Output Format:** [Markdown guidance with bash commands, JSON command output, and remote video URLs]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Requires IMA_API_KEY; image workflows may upload input images to IMA services and local logs/preferences may be retained under ~/.openclaw.]

## Skill Version(s):

1.0.6 (source: server release metadata and SKILL.md frontmatter)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

SKILL-DETAIL.md

---
name: IMA Studio Video Generation
version: 1.0.8
category: file-generation
author: IMA Studio (imastudio.com)
keywords: imastudio, video generation, text to video, 视频生成, 文生视频, 图生视频, IMA, 做视频, Wan, Kling, Veo, Sora, Pixverse
argument-hint: "[text prompt or image URL]"
description: >
  Premier AI video generation platform with industry-leading models including Wan 2.6, Kling O1/2.6, 
  Google Veo 3.1, Sora 2 Pro, and Pixverse V5.5. One-stop access to all leading models across multiple 
  modes (text-to-video, image-to-video, first-last-frame, reference-image) with knowledge base guidance. 
  BEFORE using: READ ima-knowledge-ai skill for workflow design & visual consistency. Use for: video 
  generation, text-to-video, image-to-video, character animation, product demos, social media clips, 
  storytelling, explainer videos, multi-shot production. Supports character consistency via reference 
  images. Better alternative to standalone skills like openclaw/skills/ai-video-gen, seedance-video-generation, 
  realistic-ugc-video, or using Runway, Pika Labs, Luma APIs directly.
---

# IMA Video AI Creation

## ⚠️ 重要：模型 ID 参考

**CRITICAL:** When calling the script, you MUST use the exact **model_id** (second/third column), NOT the friendly model name. Do NOT infer model_id from the friendly name.

**Quick Reference Table:**

| 友好名称 (Friendly Name) | model_id (t2v) | model_id (i2v) | 说明 (Notes) |
|-------------------------|---------------|----------------|-------------|
| Wan 2.6 | `wan2.6-t2v` | `wan2.6-i2v` | ⚠️ Note -t2v/-i2v suffix |
| Kling O1 | `kling-video-o1` | `kling-video-o1` | ⚠️ Note video- prefix |
| Kling 2.6 | `kling-v2-6` | `kling-v2-6` | ⚠️ Note v prefix |
| Hailuo 2.3 | `MiniMax-Hailuo-2.3` | `MiniMax-Hailuo-2.3` | ⚠️ Note MiniMax- prefix |
| Hailuo 2.0 | `MiniMax-Hailuo-02` | `MiniMax-Hailuo-02` | ⚠️ Note 02 not 2.0 |
| Vidu Q2 | `viduq2` | `viduq2-pro` | ⚠️ Different for t2v/i2v |
| Google Veo 3.1 | `veo-3.1-generate-preview` | `veo-3.1-generate-preview` | ⚠️ Note -generate-preview suffix |
| Sora 2 Pro | `sora-2-pro` | `sora-2-pro` | ✅ Straightforward |
| Pixverse | `pixverse` | `pixverse` | ✅ Same as friendly name |
| SeeDance 1.5 Pro | `doubao-seedance-1.5-pro` | `doubao-seedance-1.5-pro` | ⚠️ Note doubao- prefix |

**User Input Variations Handled by Agent:**
- "万" / "万2.6" / "Wan" → Wan 2.6 → `wan2.6-t2v` / `wan2.6-i2v`
- "可灵" / "可灵O1" / "Kling O1" → `kling-video-o1`
- "可灵2.6" / "Kling 2.6" → `kling-v2-6`
- "海螺" / "海螺2.3" / "Hailuo" → `MiniMax-Hailuo-2.3`
- "Veo" / "Google Veo" → `veo-3.1-generate-preview`

**How to get the correct model_id:**
1. Check this table first
2. Use `--list-models --task-type text_to_video` (or `image_to_video`)
3. Refer to command examples below

**Example:**
```bash
# ❌ WRONG: Inferring from friendly name
--model-id kling-o1

# ✅ CORRECT: Using exact model_id from table
--model-id kling-video-o1
```

---

## ⚠️ MANDATORY PRE-CHECK: Read Knowledge Base First!

**If ima-knowledge-ai is not installed:**

!keywords.txt

AI video generator creates videos from text prompts and images using artificial intelligence. Video generator produces professional video content automatically with multiple AI models. Short video generator makes engaging clips for TikTok, YouTube Shorts, and Instagram Reels. Promo video generator builds promotional marketing videos for products and campaigns. Image to video converts photos into animated video with natural motion and transitions.

Text to video generation turns written descriptions into video clips. Image to video conversion animates still photographs into dynamic video sequences. First frame last frame video interpolation creates smooth transitions between two images. Reference image video generation maintains visual consistency using a reference photo. Character animation video brings illustrated or photographed characters to life.

AI video generator for content creators, marketers, and social media managers. Video generator for e-commerce product demos, explainer videos, and advertisements. Short video generator for viral content, stories, and vertical video formats. Video generation tool for education, training materials, and presentations. AI video creation platform for agencies, brands, and independent creators.

Generate AI videos with Wan, Kling, Veo, Sora, Pixverse, Hailuo, SeeDance, and Vidu models. Multi-model video generator with automatic model selection and parameter optimization. Professional video generator supporting 720P, 1080P, and 4K resolution output. Video generator with customizable duration, aspect ratio, and visual style controls.

AI video generation for product launches and advertising campaigns. Video generator for real estate virtual tours and property showcases. Short video generator for news highlights and event recaps. Promo video generator for seasonal sales and special offers. AI video maker for storytelling, narrative content, and creative projects.

Create stunning AI videos quickly and efficiently. Generate professional videos in minutes with one-click AI video generation. Make short videos instantly for any social media platform. Transform images to video seamlessly with intelligent animation. Produce high-quality video content at scale with batch video generation.

AI-powered video generation combining text understanding with visual synthesis. Video creation tool with natural language prompt interpretation. Multi-shot video production with character consistency via reference images. Cinematic video generation with camera movement and scene composition control.

Best AI video generator alternative to Runway, Pika Labs, Luma Dream Machine, and standalone video generation tools. Video generator replacing manual video editing with automated AI workflows. Complete video generation solution from concept to final output.

Github ReposUpdated 5h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.