Use Videos Avatar Image 2video with Comfy Router

Call kling/videos-avatar-image2video through Comfy Router: endpoint, request shape and the response Router returns.

API Reference for kling/videos-avatar-image2video, served by Comfy Router from Kling.

Quick start

Create a key at platform.comfy.org/profile/api-keys and export it as COMFY_API_KEY. The Python and TypeScript snippets use the Comfy SDKs (pip install comfy-sdk, npm install @comfyorg/sdk); the cURL snippet is the same call over raw HTTP.

Model ID: kling/videos-avatar-image2video

Endpoint: POST https://api.comfy.org/v2/models/kling/videos-avatar-image2video

Python

from comfy_sdk import Comfy

# Reads COMFY_API_KEY from the environment. Each call sends a fresh
# Idempotency-Key and waits up to 10 minutes for the finished result.
with Comfy() as client:
    result = client.models.run(
        "kling/videos-avatar-image2video",
        {
            "image": "https://example.invalid/kling/avatar.png",
            "mode": "std",
            "prompt": "The presenter smiles and gestures towards the camera.",
            "sound_file": "https://example.invalid/kling/voice.mp3",
        },
    )

print(result)

Schema

Input

audio_id · string

Audio ID Generated via TTS API. Only supports 2-300 second audio generated within the last 30 days. Either audio_id or sound_file must be provided (mutually exclusive).

callback_url · string (uri)

The callback notification address for the result of this task.

Format: uri

external_task_id · string

Customized Task ID. Must be unique within a single user account.

image · string · required

Avatar Reference Image. Supports Base64 encoding or image URL. Supported formats: .jpg/.jpeg/.png. Max 10MB, min 300px width/height, aspect ratio between 1:2.5 and 2.5:1.

mode · string · default: "\"std\""

Video generation mode. std: Standard Mode (cost-effective), pro: Professional Mode (longer duration, higher quality).

Possible values: std, pro

prompt · string

Positive text prompt. Can define avatar actions, emotions, and camera movements.

sound_file · string

Sound File. Supports Base64-encoded audio or accessible audio URL. Accepted formats: .mp3/.wav/.m4a/.aac (max 5MB), 2-300 seconds. Either audio_id or sound_file must be provided (mutually exclusive).

watermark_info · object

watermark_info.enabled · boolean

Whether to generate watermarked results simultaneously.

Generated from the schema Router serves at GET /v2/models/kling/videos-avatar-image2video/openapi.json, the same document it validates a call against before the request reaches the provider.

Output

Router does not publish an output schema for this model.

Examples

Input

{
  "image": "https://example.invalid/kling/avatar.png",
  "mode": "std",
  "prompt": "The presenter smiles and gestures towards the camera.",
  "sound_file": "https://example.invalid/kling/voice.mp3"
}

Before you ship

The snippets above are the shortest working call. Three things are the same for every model and are documented once on the Comfy Router headers page: send an Idempotency-Key on every paid call and reuse it when you retry, expect the connection to be held up to Router’s 10 minute deadline, and keep X-Comfy-Request-Id from every response. The SDKs do all three for you; the cURL tab does none of them. On failure, X-Comfy-Error-Type names the bucket, and a 422 means the body failed the model’s schema and was never billed.

Headers

Authentication, idempotency, request IDs, error buckets, retry pacing, spend limits.

Quick Start

Typed error handling in Python and TypeScript, reading the 422, walking the catalog.

Limitations

What Router does not do today, and what to use instead.