Skip to main content
Glama

kling_generate_video_from_image

Animate a start image into a video or create a transition between start and end images. Describe the motion in a prompt.

Instructions

Generate AI video using reference images as start and/or end frames.

This allows you to control the video by specifying what the first frame
and/or last frame should look like. Kling will generate smooth motion between them.

Use this when:
- You have a specific image you want to animate
- You want to create a video transition between two images
- You need precise control over the video's visual content

At least one of start_image_url or end_image_url must be provided.

Returns:
    Task ID and generated video information including URLs and state.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
promptYesDescription of the video motion and content. Describe what should happen in the video, how objects should move, what transitions to include.
start_image_urlNoURL of the image to use as the first frame of the video. The video will animate from this image.
end_image_urlNoURL of the image to use as the last frame of the video. The video will animate towards this image.
modelNoKling model to use. Default: 'kling-v2-master'.kling-v2-master
modeNoGeneration mode. 'std' (standard, default), 'pro' (higher quality), or '4k' (native 4K, only for kling-v3 and kling-v3-omni).std
aspect_ratioNoVideo aspect ratio. Usually should match your input image ratio.16:9
durationNoVideo duration in seconds. For kling-v3/kling-v3-omni: 3-15 (integer). Other models: 5 or 10.
generate_audioNoWhether to generate audio synchronously. Supported by kling-v3, kling-v3-omni, and kling-v2-6 (pro mode only).
negative_promptNoThings to avoid in the video.
cfg_scaleNoClassifier-free guidance scale. Higher values follow the prompt more strictly.
camera_controlNoCamera control as JSON string.
element_listNoList of reference subjects from the subject library. Each item should contain an 'element_id'. If a reference video is present, reference subjects + reference images must be ≤ 4; otherwise ≤ 7.
video_listNoList of reference videos. Each item should contain a 'video_url' (MP4/MOV, 3-10s, 720-2160px, 24-60fps, ≤200MB, max 1 video) and optionally 'refer_type' ('feature' or 'base', default 'base') and 'keep_original_sound' ('yes' or 'no').
timeoutNoTimeout in seconds for the API to return data. Default is 300.
callback_urlNoWebhook callback URL for asynchronous notifications.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must fully disclose behavior. It only states what the tool does and the return type ('Task ID and generated video information'), but omits crucial details: whether generation is synchronous or asynchronous, how to handle long-running tasks, error scenarios, or authentication needs. The presence of callback_url and timeout parameters hints at async, but this is not explained.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is reasonably concise (10 lines), with a clear structure: main action, how it works, usage conditions, constraint, return info. The line 'This allows you to...' is somewhat redundant but not harmful. It front-loads the key purpose effectively.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (15 parameters, no annotations, output schema exists but not detailed), the description covers the core concept and usage scenarios. However, it lacks context on the asynchronous nature (e.g., polling with get_task), error handling, or how to interpret the return state. The output schema may cover return values, but the workflow is not fully explained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the description adds limited value beyond the individual parameter descriptions. It does clarify the requirement that at least one image URL is needed, which is not explicitly stated in the schema validation. Baseline 3 is appropriate as the description provides some extra context but does not significantly enhance understanding of each parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Generate AI video using reference images as start and/or end frames.' which is a specific verb+resource. It distinguishes from sibling tools like kling_generate_video (text-to-video), kling_extend_video (video extension), etc., by focusing on image-based generation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit 'Use this when:' bullet points and a clear constraint ('At least one of start_image_url or end_image_url must be provided'). It does not explicitly exclude other contexts or mention alternatives like kling_generate_video for text-only prompts, but the guidance is clear for its intended use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/AceDataCloud/KlingMCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server