Kling v1.6 Pro is a text-to-video model that turns written descriptions and reference images into fully rendered 1080p video clips, up to 10 seconds long. If you've ever wanted to produce short video content without a camera crew, animation software, or editing skills, this fills that gap. Type what you want to see, optionally anchor the opening or closing frame with a photo, and the model does the rest. The model generates video in three aspect ratios: 16:9 for widescreen presentations, 9:16 for vertical social content, or 1:1 for square posts. A negative prompt field lets you explicitly exclude unwanted elements, from blurry motion to cluttered backgrounds. The cfg_scale control lets you tighten or loosen the model's adherence to your prompt, giving you disciplined fidelity or more open-ended visual variation in the same scene. This fits naturally into social content pipelines, product demo creation, or anywhere you need short video assets without production overhead. Drop in a reference image to anchor the visual style, write a clear scene description, and run it in seconds. The results download directly, no post-processing required.
Kling v1.6 Pro generates short HD video clips directly from text, making it practical for anyone who needs video content without cameras, editing suites, or animation know-how. On Picasso IA, you type a scene description, optionally anchor a frame with a photo, and receive a finished 1080p video in seconds. It handles portrait reels, landscape presentations, and square posts equally well, so you're not locked into one platform format. Whether you're mocking up an ad concept, building a social content batch, or testing a visual idea fast, the model delivers results you can actually use.
Do I need programming skills or technical knowledge to use this? No, just open Kling v1.6 Pro on Picasso IA, adjust the settings you want, and hit generate.
Is it free to try? Picasso IA offers free credits to get started. Check the current plan details on the pricing page to see how many generations are included.
How long does it take to get results? Most clips render in under a minute. The 10-second option at 1080p takes slightly longer than the 5-second clip, but both finish well within a typical work pause.
What output formats are supported? The model outputs standard video files suitable for direct upload to social platforms, embedding in presentations, or use in video editors.
Can I customize the output quality or style? Yes. The cfg_scale slider controls how closely the model sticks to your prompt. A higher value produces results that match your description more literally; a lower value introduces more visual variation. The negative prompt field lets you block unwanted styles or elements.
How many times can I run the model? You can run multiple generations in the same session. Each run produces a new clip based on your current settings, so you can iterate on the same concept or branch into different directions without starting over.
What happens if I'm not happy with the result? Adjust your prompt, swap the reference image, change the aspect ratio, or shift the cfg_scale value and run again. Small changes to the prompt often produce noticeably different outputs.
Everything this model can do for you
Renders video at full HD resolution for clean, publication-ready results.
Choose between 5-second and 10-second clips to match your content format.
Generate in 16:9, 9:16, or 1:1 to fit any platform without cropping.
Lock the first or last frame with a reference photo to control the visual start and end of the clip.
Exclude specific elements, styles, or artifacts to steer results away from unwanted content.
Adjust cfg_scale to balance strict prompt fidelity against more varied visual output.
Attach up to 4 reference photos to shape the visual style and subject matter of the video.
Fast, automated video creation for any content need
Create a realistic, heartwarming animation of a capybara relaxing in a bathtub, sitting upright with water rippling around it. The capybara's front paws are rubbing its round belly gently, mimicking the motions of washing itself. The actions should be smooth, slightly quick, and natural, as if the capybara is enjoying a self-cleaning bath. Ensure the setting includes soft, warm lighting, steam rising slightly from the water, and visible water droplets on its fur. The overall vibe should convey calmness and contentment.
A white human-like cat wears a red and blue Super Mario costume. She kneads a large ball of bread dough while flour floats in the air. The camera pans around the cat. The light comes through the window making the fur, costume and dough look more real.
Reflections in crystal mirrors, rainbow light, geometric world
