Kling V2.1 Pro is Rivya's legacy two-frame Kling option for image-to-video shots that need a start frame and an optional tail frame. It is the practical choice when the key question is how a shot should travel from one image state to another, not whether you need text mode or newer Kling controls.
The final cost is rounded up to whole credits.

Example output
Kling V2.1 Pro
Image to Video

Example output
Kling V2.1 Pro
Best for
Supports
Try this model
No results to display yet.
Model examples
Review examples to help decide whether the model fits your task.
Model strengths
Model strengths
Suggested uses
Tasks to consider
Model details
Provider
Kuaishou
Category
Video
Capabilities
Image to Video
Credit charges
Credit rate: 50–100 per video
Inputs
Up to 2 image references
Prompt requirements
Up to 5,000 characters
Developer access
Kling V2.1 Pro can be called through Public API v1. Modes that use reference media require uploads through the Files API. Check the model reference for supported inputs.
Kling V2.1 Pro FAQ
Kling V2.1 Pro is a good fit when the shot already has a planned start and a planned end. It is a useful legacy option for reveal clips, before-and-after transitions, and storyboard checks where the creative question is not just how to animate the first frame, but how to travel from image A to image B.
On Rivya, this option is still image-to-video only, but it accepts up to two images and maps the second image to the tail frame. The public controls stay fairly simple: choose 5 or 10 seconds, use `negative_prompt` when needed, and adjust `cfg_scale` if the transition needs tighter prompt adherence.
The biggest question is whether the ending frame is real enough to deserve a two-frame project. If the tail frame already defines what the shot should land on, Pro becomes useful. If the ending state is still fuzzy, the extra cost is often hard to justify and the cheaper Standard option is usually the better proving ground.
Rivya currently lists 50 credits for 5 seconds and 100 for 10. That spend makes more sense when the transition itself is the job, because the tail frame saves you from leaving the destination vague. In practice, 5 seconds is often enough to prove the handoff, while 10 seconds is better reserved for shots that need more breathing room.
Choose Kling V2.1 Standard when one opening frame is enough and the ending state is still loose. Choose newer Kling options when you need broader controls or text-led generation. Choose Kling V2.1 Pro when you already know where the shot should start, where it should land, and you want that planned transition to be the whole point of the run.
Start here when the first result needs to answer one specific question: can this shot travel cleanly from the chosen first frame to the chosen ending frame? Use it for reveal clips, before-and-after transitions, and storyboard tests where the two-frame plan matters from the start.
This page is a two-image image-to-video option. Before the first result, you can upload a starting frame, optionally add a second image as the tail frame, choose 5 or 10 seconds, and use `negative_prompt` or `cfg_scale` if the transition needs more control.
First check whether the second image really represents the landing frame you want, because that is what makes Pro different from Standard. Then decide whether 5 seconds is enough to prove the transition before paying for 10, and only tighten `cfg_scale` or add a `negative_prompt` when the path between the two frames needs more steering.
The page is public, but the actual image-to-video run is still gated behind sign in. Rivya currently lists 50 credits for 5 seconds and 100 for 10, so you can settle the start frame, the tail frame, and the duration first, then sign in when you are ready to generate.
Stay on this page while you are checking one start-frame plus tail-frame pair and checking whether the planned transition is working. Open the full Studio once the project needs saved versions, multiple transition branches, or a longer sequence built around the same reveal or shot progression.
Compare alternatives
Create Seedance 2.5 videos from text, a start frame with an optional end frame, or image, video, and audio references. Choose 480p, 720p, or 1080p, a duration from 4 to 30 seconds or automatic duration, and an MP4 or MOV format request.
Why consider it
Input option: Up to 50 reference files
Generate video from text, a first frame, or media references.
Why consider it
Input option: Prompt, first frame with optional last frame, or image/video/audio references
ByteDance's Seedance 2.0 Fast video model for text prompts, a first frame with an optional last frame, or image, video and audio references. Choose 480p or 720p, set a 4–15-second duration, and request audio or a returned last frame.
Why consider it
Input option: Prompt, first frame with optional last frame, or image/video/audio references