Kling 
WaveSpeed Text and image to video generation
Kling 3.0 Pro is a video generation model developed by Kling, designed to produce video content from both text prompts and image inputs. It represents the 3.0 Pro tier of Kling's video model lineup, with a training cutoff of February 2026 and availability on MindStudio starting March 2026. The model accepts text descriptions, image URLs, and configurable selection parameters to control output characteristics.
Kling 3.0 Pro is suited for workflows that require generating video from written descriptions or existing images, making it applicable to content creation, prototyping, and visual storytelling tasks. Its support for both text-to-video and image-to-video modalities gives it flexibility across different starting points for video production. The model operates with a context window of 10,000 tokens, accommodating detailed prompts for more precise video generation.
What Kling 3.0 Pro supports
Text to Video
Generates video clips directly from written text prompts, supporting up to 10,000 tokens of context for detailed scene descriptions.
Image to Video
Animates or extends a provided image URL into a video sequence, using the source image as a visual starting frame.
Configurable Output Settings
Accepts multiple select-type inputs at inference time, allowing users to control generation parameters such as duration, aspect ratio, or style.
Prompt-Driven Control
Uses natural language text input to guide video content, motion, and composition, enabling precise creative direction through descriptive prompting.
Ready to build with Kling 3.0 Pro?
Get Started FreeCommon questions about Kling 3.0 Pro
What is the context window for Kling 3.0 Pro?
Kling 3.0 Pro has a context window of 10,000 tokens, which applies to the text prompt input used to guide video generation.
What input types does Kling 3.0 Pro accept?
The model accepts image URLs, text prompts, and multiple select-type parameters, supporting both text-to-video and image-to-video generation workflows.
When was Kling 3.0 Pro trained?
Kling 3.0 Pro has a training date of February 2026, meaning its knowledge and visual capabilities reflect data available up to that point.
Do I need an API key to use Kling 3.0 Pro on MindStudio?
No API key is required to use Kling 3.0 Pro on MindStudio. The model is accessible directly through the MindStudio platform.
What is the difference between the text-to-video and image-to-video modes?
In text-to-video mode, the model generates a video solely from a written prompt. In image-to-video mode, a provided image URL serves as the visual starting point, which the model then animates or extends into a video sequence.
Documentation & links
Parameters & options
Description of what to exclude from the video.
Whether sound is generated simultaneously when generating a video.
Explore similar models
Kling Kling 3.0
Kling
Kling Kling 2.6
Kling
Kling Kling 3.0 Motion Control
Kling 3.0 Standard Motion Control transfers motion from reference videos to animate still images.
Lightricks LTX-2.3 LoRA
LTX-2.3 LoRA is a fine-tuning extension for Lightricks' LTX-2.3 video generation model, enabling custom character, style, and camera control in AI-generated videos.
MiniMax Hailuo 2.3 Pro
MiniMax Hailuo 2.3 Pro is a video generation model for ultra-clear 1080P output and physics-aware scenes with responsive rendering.
ByteDance DreamActor V2
ByteDance DreamActor V2 is a motion transfer model that animates any character — human, cartoon, or creature — by applying movements from a reference video to a static image.
Start building with Kling 3.0 Pro
No API keys required. Create AI-powered workflows with Kling 3.0 Pro in minutes — free.