Kling Video
Kling video from text or a start frame, with an optional end frame and sound. Runs Kling 3.0 Pro by default; Model also offers 3.0 Standard, 2.6 Pro, O1, 2.5 Turbo and 2.1 Master. Kling 4.0 is its own node.
Try Kling Video in the playground
Kling Video
Node type: video:kling_video_2_5_i2v
Category: video
Description
Kling Video is Kuaishou's video generation model, and this Wireflow node runs several Kling versions from one card: pick 3.0-pro, 3.0-standard, 2.6-pro, o1, 2.5-pro and more under Model. It makes 5 or 10 second clips in 16:9, 9:16 or 1:1 from a prompt (text to video when no Start Frame is connected), or from a Start Frame with an optional End Frame, with optional generated audio and up to 2 voice IDs. Its node type is video:kling_video_2_5_i2v. Call it from code by running a saved workflow that contains it with POST /api/v1/workflows/{id}/run, or let an agent build and run it over the Wireflow MCP server. Shorter clips can cost a bit more per second, and you are always charged for the real length.
Pricing
- Cost: ~27 credits per second
- Per-second rate: The figure is the rate for a 5-second clip. Shorter clips can cost a bit more per second. You're always charged for the real length.
Canvas ports
These appear as port handles on the left side of the node.
| ID | Label | Details |
|---|---|---|
prompt |
Prompt | TEXT (required) |
negative_prompt |
Negative Prompt | TEXT · default: "blur, distort, and low quality" |
image_url |
Start Frame | IMAGE. Optional - uses text-to-video when not connected |
end_image_url |
End Frame | IMAGE. Optional end frame for the video |
Sidebar config
These render as form fields in the right-side config panel when the node is selected.
| ID | Label | Details |
|---|---|---|
model_version |
Model | TEXT · options: 3.0-pro, 3.0-standard, 2.6-pro, o1, 2.5-pro, 2.5-standard, 2.1-master · default: "3.0-pro" |
duration |
Duration | TEXT · options: 5, 10, 3, 4, 6, 7, 8, 9, 11, 12, 13, 14, 15 · default: "5" |
aspect_ratio |
Aspect Ratio | TEXT · options: 16:9, 9:16, 1:1 · default: "16:9" |
generate_audio |
Generate Audio | BOOLEAN · default: true |
voice_ids |
Voice IDs | TEXT. Kling 2.6 only. Kling 3.0 binds voices to character elements, which this node does not support yet. Comma-separated voice IDs for audio (max 2). Reference in prompt as <<<voice_1>>> and <<<voice_2>>> |
Outputs
| ID | Label | Type |
|---|---|---|
video |
Generated Video | VIDEO |
Auto-generated from the Wireflow node registry.