Skip to main content
Glama

seedance_generate_video_from_image

Generate AI videos from images by specifying first frame, last frame, or reference images for style and content guidance. Create transitions and motion.

Instructions

Generate AI video using reference images with ByteDance Seedance.

This allows you to control the video by specifying first frame, last frame,
or reference images. Seedance will generate smooth motion based on the inputs.

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

Note: reference_image_urls cannot be combined with first_frame_url/last_frame_url.
At least one image input must be provided.

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

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
seedNoRandom seed. -1 for random. Default is -1.
modelNoModel version to use. Use 'doubao-seedance-2-0-260128' (default) for latest-generation quality and multimodal reference, 'doubao-seedance-2-0-fast-260128' or 'doubao-seedance-2-0-mini-260615' for faster/cheaper 2.0, or a 1.x model such as 'doubao-seedance-1-0-lite-i2v-250428' for lightweight I2V.doubao-seedance-2-0-260128
ratioNoVideo aspect ratio. Use 'adaptive' to match your input image ratio.16:9
framesNoFrame count for the generated video. Must satisfy 25+4n (e.g. 29, 33, 37, ..., 361). Mutually exclusive with 'duration'.
promptYesDescription of the video motion and content. Describe what should happen in the video, how objects should move, what transitions to include.
durationNoVideo duration in seconds. Range: 2-15 (Seedance 2.0 supports 4-15). Default is 5. Mutually exclusive with 'frames'.
resolutionNoVideo resolution. Options: '480p', '720p', '1080p', '4k'. '4k' is supported only by 'doubao-seedance-2-0-260128'; '2-0-fast' and '2-0-mini' max out at '720p'.720p
callback_urlNoWebhook callback URL for asynchronous notifications.
service_tierNoService tier. 'default' or 'flex' (50%% cheaper). Default is 'default'.default
generate_audioNoIf true, generate audio. Supported by 'doubao-seedance-1-5-pro-251215' and the 'doubao-seedance-2-0' series. Default is false.
last_frame_urlNoURL of the image to use as the last frame of the video. The video will animate towards this image. Supports https:// URLs or base64 data:image/... URIs.
first_frame_urlNoURL of the image to use as the first frame of the video. The video will animate from this image. Supports https:// URLs or base64 data:image/... URIs.
return_last_frameNoIf true, return the last frame of the generated video. Default is false.
reference_audio_urlsNoSeedance 2.0 only. Reference audio URLs (up to 3) for voice timbre / background music. Ignored by 1.x models.
reference_image_urlsNoList of reference image URLs for style/content guidance. For the Seedance 2.0 series these can be real-person / character references that keep the subject consistent (up to 9). These images influence the look but are not used as frames. Cannot be combined with first_frame_url or last_frame_url.
reference_video_urlsNoSeedance 2.0 only. Reference video URLs (up to 3) for subject, camera movement, motion or overall style. Ignored by 1.x models.
execution_expires_afterNoTask timeout threshold in seconds. Default is 172800 (48 hours).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior4/5

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

No annotations provided, so the description bears full responsibility. It discloses that at least one image input is required, that reference images cannot be combined with frame URLs, and mentions the return format (task ID and video info). However, it does not detail potential limitations or side effects, but is adequate for a generative tool.

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 well-structured with bullet points for use cases and a clear note section. It is front-loaded with the core purpose and is appropriately sized given the tool's complexity (17 parameters). Minor improvement could be more brevity, but it's efficient.

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

Completeness4/5

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

Given the high parameter count, the description covers the essential functionality, usage scenarios, and key constraints. An output schema exists to detail return values, so that is not a gap. The description is sufficiently complete for an agent to select and invoke the tool correctly.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3. The description adds value by grouping parameters (first_frame_url, last_frame_url, reference_image_urls) and explaining their roles, and by noting constraints like mutual exclusivity. This goes beyond repeating schema descriptions.

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 the tool generates AI video from images using ByteDance Seedance, specifying the ability to use first frame, last frame, or reference images. This distinguishes it from sibling tools like seedance_get_task which focus on task management.

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

Usage Guidelines5/5

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

Explicitly includes 'Use this when:' with four bullet points covering specific use cases, and notes when not to use it (reference_image_urls cannot combine with first_frame_url/last_frame_url). Provides clear context for tool selection.

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/SeedanceMCP'

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