pikaffects
Add instant visual effects to a single image and export as a video.
Kling AI's Kling 4.0 Image to Video turns a start image into a 3-30 second clip at 720p or 1080p, with optional middle and end frames.
Trading a blank timeline for a locked opening frame, Kling 4.0 Image to Video helps ad, product, and previz teams move a still without rebuilding the shot.
For developers, Kling 4.0 Image to Video on RunComfy can be used both in the browser and via an HTTP API, so you don't need to host or scale the model yourself.
Ideal for: Still-to-Motion Product Shots | Storyboard Beats | Locked Opening Frames
Kling 4.0 Image to Video is the still-first pass of Kling's current video model. One opening picture plus a short motion note becomes a clip of 3 to 30 seconds at 720p or 1080p. Sound is recorded into the same file. There is no mute switch on Kling 4.0 Image to Video, so the prompt is where you name the track.
The start frame can stand alone. Kling 4.0 Image to Video can also pin a last frame, and up to eight ordered stills between those two. Start, middle, and end together stay within ten images. The frame follows the opening picture. Five seconds and 1080p are the defaults on Kling 4.0 Image to Video. Drop to 720p while you search for the move, then come back to 1080p for the keep.
This page starts from a picture. The text page writes a shot from words alone, in 16:9, 9:16, 1:1, or 21:9, while Kling 4.0 Image to Video stays on the still. The reference page can add stills, clips, and saved subjects. The editing page changes footage you already have, which Kling 4.0 Image to Video does not take as a source. All four use the same Kling 4.0 weights.
Teams keep Kling 4.0 Image to Video in the set when the same job starts as a still, a script, a set of references, or an existing clip.
These controls belong to Kling 4.0 Image to Video. The text page drops the image fields and adds an aspect ratio. The reference page adds reference media and saved subjects. The editing page starts from a source video.
| Parameter | Required | Type | Default | Range / Options | Description |
|---|---|---|---|---|---|
start_image_url* | Yes (*) | string | Example still | Image URL | Opening frame for Kling 4.0 Image to Video. The output frame follows this image. |
prompt* | Yes (*) | string | Example line | Text | Motion, camera, and sound after the opening frame. |
middle_image_urls | No | array | Empty | 0-8 images | Ordered stills Kling 4.0 Image to Video places between the opening and the close. |
end_image_url | No | string | Empty | Image URL | Optional last frame. |
duration | No | integer | 5 | 3-30 | Length in seconds for Kling 4.0 Image to Video. |
resolution | No | string | 1080p | 720p, 1080p | Output resolution for a Kling 4.0 Image to Video keep. 1080p is the default. |
Start, middle, and end images together cannot pass ten.
Kling 4.0 Image to Video bills the generated length. A start frame, middle frames, and an end frame add no separate fee. The text page uses the same rates as Kling 4.0 Image to Video. The reference page uses these rates only when you do not attach a video. The editing page, and any reference request that includes video, uses counted-second rates instead of the Kling 4.0 Image to Video still rate.
| Resolution | Rate |
|---|---|
| 720p | $0.12 per second |
| 1080p | $0.18 per second |
| Duration | 720p | 1080p |
|---|---|---|
| 5 s | $0.60 | $0.90 |
| 10 s | $1.20 | $1.80 |
| 30 s | $3.60 | $5.40 |
A 5-second 1080p file is the usual first charge on Kling 4.0 Image to Video.
Based on publicly available information for Kling 4.0 Image to Video. Length limits below are published input ranges, not a scored ranking.
| Model | Inputs | Length | Standout |
|---|---|---|---|
| Kling 4.0 Image to Video | One start image, up to eight middle frames, optional end image | 3-30 seconds | Native sound in the same file, 720p or 1080p, frame follows the opening still |
| Kling Video O3 image passes | A reference image on separate standard and 4K pages | Commonly 3-15 seconds | An earlier Kling generation, including a 4K option on its own page |
| Kling 2.6 image passes | A start image on earlier Kling video pages | Shorter published ranges | Useful when you already have a 2.6 workflow and do not need a 30-second take |
Stay with an O3 4K page when you need that resolution. Use Kling 4.0 Image to Video when the job is a 720p or 1080p shot of up to 30 seconds from a still, with sound written from the prompt.
Add instant visual effects to a single image and export as a video.
FLUX 3 Max Keyframes To Video links up to ten stills into one clip.
Prompt-based animating with subject fidelity and smooth motion.
Produces crisp 1080p AI videos with smart motion logic and speed
Create fast, audio-enhanced visuals from text prompts
Generate a 5 to 15 second scene with picture and sound from a prompt.
Kling 4.0 Image to Video animates a start image into a 3-30 second clip at 720p or 1080p. You can add an end frame and up to eight middle frames. Sound is part of the same file, and the frame follows the opening image.
Kling 4.0 Image to Video locks frame one to your still. The text page invents the shot from words and lets you pick 16:9, 9:16, 1:1, or 21:9. Use this page when the opening picture has to survive.
Yes. Kling 4.0 Image to Video takes an optional end image, and up to eight ordered middle frames between the start and the end. Start, middle, and end together stay within ten images.
Yes. Kling 4.0 Image to Video writes sound into the same file, and there is no switch to turn that track off. Name the noises you want in the prompt, such as room tone, footsteps, or a short line.
Kling 4.0 Image to Video uses a whole-second length from 3 to 30, with 5 as the default. Resolution is 720p or 1080p, and 1080p is the default. The output frame follows the start image.
For Kling 4.0 Image to Video, name one camera move, write the action in order, and list a few sounds. The still already shows the subject, so spend the prompt on what moves next. If you set an end image, describe the change that joins the two frames.
Prototype Kling 4.0 Image to Video in the RunComfy Playground Web UI, then call the same model through the RunComfy API with the same image, prompt, duration, and resolution. Jobs spend usd or credits. New accounts usually start with a trial balance.
Kling 4.0 Image to Video costs $0.12 per second at 720p and $0.18 per second at 1080p, based on the generated length. Middle frames and an end frame add no separate fee. A 5-second 1080p clip is $0.90.
RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.
