Ray 3.2 takes a text prompt and generates a cinematic 5-second or 10-second video without any camera gear or video editing experience. You describe the subject, motion, camera angle, and lighting in plain language, and the model handles the production entirely. The result lands in your exports folder as a finished MP4, ready for review. Outputs go up to 1080p, with an optional HDR encoding mode for scenes that need extended dynamic range in highlights and shadows. Turn on EXR export alongside HDR and you get a raw color file you can bring into a professional grading suite. For image-to-video work, you can pin a specific photo as the opening frame, the closing frame, or both, so the clip starts and ends exactly where you intend. Ray 3.2 fits into both quick ideation rounds and production workflows. A social media creator can generate a looping vertical clip in minutes; a post-production team can pull 1080p HDR footage to composite with other elements. Write your prompt, choose your settings, and the model takes it from there.
Ray 3.2 is a video generation model that turns a text prompt or a reference image into a short cinematic clip, bridging the gap between a written concept and a watchable video file. On Picasso IA, you can produce 5-second or 10-second clips at resolutions from 540p to 1080p, across aspect ratios from 9:16 portrait to 21:9 cinematic widescreen. The model reads your description of subject, motion, and lighting, then determines how the scene should move and how the camera should behave. HDR output and EXR export are available for creators who need footage that drops straight into a color-grading pipeline without conversion.
Do I need programming skills or technical knowledge to use this? No, just open Ray 3.2 on Picasso IA, adjust the settings you want, and hit generate.
Is it free to try? You can run Ray 3.2 without installing any local software or setting up infrastructure. Credits are used per generation; see the pricing page for current rates.
How long does it take to get results? A 5-second clip at 720p typically returns in under a minute. Longer clips or 1080p outputs take a bit more processing time depending on server load.
Can I use my own image as the first or last frame? Yes. Upload a start image to anchor the opening shot, an end image to define where the clip lands, or both together for a controlled frame-to-frame transition. This is available on 5s duration only.
What is HDR mode and when should I use it? HDR encodes a wider range of brightness and color into the output MP4. Use it when the footage will be shown on HDR-capable screens or brought into a color-grading workflow. HDR requires 720p or 1080p resolution and 5s duration, and cannot be combined with the loop option.
What is EXR export? EXR is an open, high-dynamic-range file format used in professional post-production pipelines. When you enable EXR export alongside HDR, you receive both a finished MP4 and the raw EXR data ready for a full grading pass in professional color-grading software.
Can I generate a looping video? Yes. The loop option produces a clip that cycles back to its start without a visible cut. It is only available at 5s duration and cannot be combined with HDR output or an end image.
Everything this model can do for you
Generate MP4 files with high dynamic range at 720p or 1080p for richer highlights and shadow detail.
Download a raw EXR file alongside the MP4 to bring your clip into a professional color-grading suite.
Choose between 5-second and 10-second clips to match your project's pacing and platform requirements.
Set a start image, an end image, or both to define the visual bookends of your generated video.
Output in 9:16, 3:4, 1:1, 4:3, 16:9, or 21:9 without needing to crop or reformat after export.
Produce a looping video that cycles without a visible cut, ready for use as a background or animated asset.
Use any photo or illustration as the first frame and let the model animate forward from that starting point.
