Image and Video Generation

Use VibeVideo directly from Claude Code to generate images and videos with natural language.

Overview

The VibeVideo Claude Code Skill lets you generate AI images and videos directly from Claude Code using natural language prompts. No installation required — only an API key.

Prerequisites

A VibeVideo API key — create one at Dashboard → Settings → API Keys
Claude Code installed (claude.ai/code)

Setup

Set your API key as an environment variable:

export VIBEVIDEO_API_KEY="your-api-key-here"

Save the skill file to your project's .claude/skills/ directory:

mkdir -p .claude/skills/vibevideo-generate

Create .claude/skills/vibevideo-generate/SKILL.md — copy the content from the SKILL.md source file

Usage

Once configured, just ask Claude Code naturally:

"Generate an image of a cat sitting on a rainbow"
"Create a 5-second video of ocean waves at sunset"
"What image models are available?"

How It Works

The skill calls the VibeVideo REST API via curl:

Create task — POST /api/ai/generate with your prompt, model, and options
Poll status — POST /api/ai/query every 5 seconds until complete
Return result — media URLs from taskUrls

Authentication uses the Authorization: Bearer <API_KEY> header. Credits are deducted per generation — same as the web dashboard.

Generate Image

curl -s -X POST ${VIBEVIDEO_BASE_URL:-https://vibevideo.app}/api/ai/generate \
  -H "Authorization: Bearer $VIBEVIDEO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "mediaType": "image",
    "scene": "text-to-image",
    "model": "nano-banana-2",
    "prompt": "A cat sitting on a rainbow",
    "options": {
      "aspect_ratio": "1:1",
      "quality": "2K"
    }
  }'

For image-to-image, set "scene": "image-to-image" and add "image_url" in options.

Generate Video

curl -s -X POST ${VIBEVIDEO_BASE_URL:-https://vibevideo.app}/api/ai/generate \
  -H "Authorization: Bearer $VIBEVIDEO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "mediaType": "video",
    "scene": "text-to-video",
    "model": "seedance-2-0",
    "prompt": "A dog playing in a park",
    "options": {
      "resolution": "720p",
      "duration": "5s",
      "aspect_ratio": "16:9"
    }
  }'

For image-to-video, set "scene": "image-to-video" and add "image_url" in options. For frames-to-video, add "start_image_url" and "end_image_url" in options.

Query Task Status

Tasks are asynchronous. Poll until status is success, failed, or canceled:

curl -s -X POST ${VIBEVIDEO_BASE_URL:-https://vibevideo.app}/api/ai/query \
  -H "Authorization: Bearer $VIBEVIDEO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "taskId": "YOUR_TASK_ID" }'

Calculate Cost

Check credit cost before generating:

curl -s -X POST ${VIBEVIDEO_BASE_URL:-https://vibevideo.app}/api/ai/cost \
  -H "Authorization: Bearer $VIBEVIDEO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2-0",
    "mediaType": "video",
    "scene": "text-to-video",
    "options": { "resolution": "720p", "duration": "5s" }
  }'

Cancel Task

curl -s -X DELETE ${VIBEVIDEO_BASE_URL:-https://vibevideo.app}/api/ai/tasks/YOUR_TASK_ID \
  -H "Authorization: Bearer $VIBEVIDEO_API_KEY"

Image Models

ID	Label	Vendor	Scenes	Qualities
nano-banana-2	Nano Banana 2	Google	text-to-image, image-to-image	1K, 2K, 4K
gpt-image-1-5	GPT Image 1.5	OpenAI	text-to-image, image-to-image	Medium, High
grok-imagine	Grok Imagine	Grok	text-to-image, image-to-image	—
seedream-5-0	Seedream 5.0	ByteDance	text-to-image, image-to-image	Basic, High
qwen-image	Qwen Image	Qwen	text-to-image, image-to-image	—
wan-2-7-image	Wan 2.7 Image	Qwen/Alibaba	text-to-image, image-to-image	1K, 2K
wan-2-7-image-pro	Wan 2.7 Image Pro	Qwen/Alibaba	text-to-image, image-to-image	1K, 2K, 4K

Default for text-to-image: nano-banana-2

Video Models

ID	Label	Vendor	Scenes	Resolutions	Durations
seedance-2-0	Seedance 2.0	ByteDance	text-to-video, image-to-video, frames-to-video, reference-to-video	720p, 1080p	5s, 10s, 15s
seedance-2-0-fast	Seedance 2.0 Fast	ByteDance	text-to-video, image-to-video, frames-to-video, reference-to-video	720p, 1080p	5s, 10s, 15s
seedance-1-5-pro	Seedance 1.5 Pro	ByteDance	text-to-video, image-to-video	480p, 720p, 1080p	4s, 8s, 12s
grok-imagine	Grok Imagine	Grok	text-to-video, image-to-video	480p, 720p	6s, 10s, 15s
kling-2-6	Kling 2.6	Kling	text-to-video, image-to-video	—	5s, 10s
runway	Runway	Runway	text-to-video, image-to-video	720p, 1080p	5s, 10s
veo-3-1	Veo 3.1	Google	text-to-video, image-to-video, frames-to-video, reference-to-video	720p, 1080p, 4k	—
veo-3-1-fast	Veo 3.1 Fast	Google	text-to-video, image-to-video, frames-to-video, reference-to-video	720p, 1080p, 4k	—
seedence-1-0-pro	Seedence 1.0 Pro	ByteDance	text-to-video, image-to-video	480p, 720p, 1080p	5s, 10s
seedence-1-0-pro-fast	Seedence 1.0 Pro Fast	ByteDance	image-to-video	720p, 1080p	5s, 10s
seedence-1-0-lite	Seedence 1.0 Lite	ByteDance	text-to-video, image-to-video	480p, 720p, 1080p	5s, 10s

Default for text-to-video: seedance-2-0

Error Handling

Code	Message	Solution
-1	"no auth"	Set `VIBEVIDEO_API_KEY` environment variable
-1002	"insufficient credits"	Purchase credits at VibeVideo dashboard
-1	"invalid..."	Check model ID, scene, or mediaType against the tables above

API Response Envelope

All endpoints return:

{ "code": 0, "message": "ok", "data": { ... } }

code: 0 means success. Non-zero code means error (check message).

Image and Video Generation

On this page