Gen 4.5 is a text-to-video model that turns written descriptions into short, high-quality video clips. If you have ever had a clear visual idea but no footage to work with, this model closes that gap. It produces fluid, consistent motion and sticks closely to what you describe, so the output actually reflects your intent. You can generate clips up to 10 seconds long across six aspect ratios, from vertical 9:16 for social content to ultra-wide 21:9 for widescreen formats. Optionally supply a starting image to anchor the first frame and let the model animate forward from there. Tight prompt adherence means a specific scene description yields a specific result, rather than a generic clip that barely resembles what you asked for. Gen 4.5 fits naturally into content workflows where you need quick video without production equipment or screen recording. Write your prompt, set the duration and aspect ratio, run the model, and drop the output directly into your project.
Gen 4.5 is a text-to-video model built for creators, marketers, and anyone who needs to turn a written idea into a short video clip without a camera, editing suite, or any technical knowledge. On Picasso IA, the process is direct: write a prompt, set your duration and aspect ratio, and generate. The model is built for motion quality and prompt adherence, so the clip you get back looks deliberate, not generic. It handles social media shorts, vertical story formats, and widescreen cinematic intros, all from a text prompt.
Do I need programming skills or technical knowledge to use this? No, just open Gen 4.5 on Picasso IA, adjust the settings you want, and hit generate.
Is it free to try? Yes, you can run Gen 4.5 on Picasso IA without paying upfront. Check your account dashboard for any generation credits or limits that apply to your plan.
How long does it take to get results? Generation time depends on clip duration and current server load. A 5-second clip typically finishes faster than a 10-second one. Most runs finish within a few minutes.
What output formats are supported? The model returns a video file you can download directly from the results page. From there, import it into any video editor or upload it to any platform that accepts standard video files.
Can I customize the output quality or style? You control the prompt, aspect ratio, duration, and seed. The more specific your prompt is about scene details, lighting, and motion, the closer the output matches your vision.
How many times can I run the model? You can run the model as many times as you need. Each generation is independent, so you can iterate with different prompts or settings without losing previous results.
Where can I use the outputs? The video clips you generate belong to you. Use them in social media posts, presentations, client mockups, ads, or any project where you need short video content.
The credit cost for this model varies based on the settings you choose. Below are the costs per configuration:
Everything this model can do for you
Produces fluid, artifact-free movement that holds consistent detail across every frame.
The video output closely reflects what you write, reducing the need for multiple retakes.
Provide a starting image to pin the first frame and animate forward from there.
Choose from 9:16, 16:9, 4:3, 3:4, 1:1, or 21:9 to match any platform or format.
Set the clip length to 5 or 10 seconds depending on what your project needs.
Set a seed value to reproduce the exact same clip when consistency matters.
Works without any reference image, generating video from a written description alone.
A scene in new york city where all the cars and cabs start floating up. We see a girl watching the scene from the back. indie aesthetic, daytime
A scene in new york city where all the cars and cabs start floating up. We see a girl watching the scene from the back
A raccoon in a plain room in zero gravity trying to steal the garbage from a silver trash can. The garbage floats out in zero gravity. Handheld documentary film style. Natural camera shake. Raw indie film aesthetic. Natural lighting. Unpolished, authentic look. Low budget realism. Observational feel.
A dense, verdant jungle world made up of small lego-like pieces. We see a rainbow chameleon running through the 3D world, the camera in and out of focus.
