↓
Rivya AI Docs

Rivya Video Studio: Generate and Review a Clip

Learn how to choose a video model, upload compatible references, check settings and credits, review the full clip, and save the result in Rivya Video Studio.

Last reviewed on November 11, 2026

Video Studio is Rivya’s signed-in workspace for submitting video tasks and reviewing their results. Start with one scene, such as a product shot with a slow camera move. A generated clip still needs review and may need editing before publication.

Separate generation, editing and upscaling

Gemini Omni 1.2 Flash has distinct reference, first/last-frame and video-edit modes. Keep frame input separate from references or video. Editing follows the server-verified source duration and does not send the generation duration field.

Grok Imagine Video 1.5 Preview now includes a priced 1080p option while retaining its one-image input limit. Rivya Video Upscale processes an existing clip within a selected output box; it does not turn a text prompt into a new scene. Review source duration and the current reserve before submitting either video operation.

Choose a model for your starting material

Check the model directory and availability guide. Choose a model that is available in Studio; a public listing can also describe a paused or Coming Soon model. The inputs you can use depend on the selected model and mode.

Starting materialWhat to check before choosing
Text describing a sceneThe model supports text-to-video and the required settings
A still image you have reviewedThe model accepts an image in the role you need
First and last framesThe selected mode accepts opening and closing frames; ordinary references do not automatically become those frames
A reference video or motion exampleThe model supports that video input and the intended operation
A portrait or video plus a speech recordingThe model supports the required image/audio or video/audio combination

If the product appearance is still undecided, prepare and review a still in Image Studio. For supported reference roles, see video references. These are different model capabilities, not modes every video model includes.

Submit a focused first task

  1. Sign in and select the model and input mode. Choose one scene and the movement you want to check.

  2. Upload the required files and wait for each upload to finish. Check which attachments appear in the form, including dedicated frame or reference fields. Check the selected model’s file count, format, size, dimensions, and duration limits in references and uploads.

  3. Where the model accepts a prompt, describe the opening, main motion and ending. Identify what should remain unchanged in the subject.

  4. Choose the available duration, aspect ratio, resolution, and audio settings for where you will use the clip. Check the displayed credit estimate before submitting.

  5. Submit the request and follow the task’s status once a task is created. When a playable result is available, watch the whole clip and save the version you want to keep before another attempt.

For a model that accepts an image reference, you could write:

Use the attached bottle photo as the visual reference. Begin with the bottle centered on a plain desk. Slowly move the camera closer while the bottle stays still. End with the whole bottle and label in view. Do not add objects or change the bottle’s color.

This is an illustrative prompt, not a tested result. The generated product may still differ from the reference photo. See prompt-writing basics for clearer instructions.

Check settings and audio separately

Choose vertical, square or horizontal only where the selected model offers that ratio. Use quality, duration and aspect ratio to match the output to its destination. Available durations and resolutions vary; writing “4K” in the prompt does not select a resolution. Choose a short test only if it lets you judge the movement you need. Several test runs can still increase the total cost of the project.

Some models generate audio with video; others use uploaded speech or audio references. Generating a soundtrack and using an uploaded recording are different operations. Check the selected model’s audio controls, then play the result to hear what it actually produced. See audio uploads for input constraints.

For separate narration or music, check the available options in Audio Studio before planning your edit. Suno Music supports new custom-mode generation. Music extension, WAV conversion and vocal separation from Music results remain unavailable. Use a suitable editor to combine separate audio with a finished video; Audio Studio does not automatically attach it to an existing video, mix a soundtrack, or make localized versions.

Changing the video model can reset parameters and remove unsupported or excess attachments. Recheck the entire form, including frame inputs, before sending another task.

Review the whole clip and save the usable files

Watch from beginning to end at the intended display size. Check subject shape, product color and label, hands, edges, reflections, unwanted objects, camera movement, opening and ending, and any audio timing or unexpected speech. A plausible motion is not evidence that the real product works that way. Use the commercial review checklist before publishing.

Interface text, subtitles, logos, and detailed on-screen copy may need a separate editor. For multiple scenes, you will also need to choose the clips and assemble them. Video Studio does not provide a complete editing timeline.

Find submitted tasks in History, use the Notifications Center for updates, and download accepted outputs. Keep your own source files, approved prompt, model settings, and downloaded outputs. See Saved sessions for what Rivya records. You will still need your own editing project and file copies; links to source or output files may stop working later.

Understand retries and result operations

Each new generation has a cost. The estimate can depend on the model, duration, quality, audio, or reference inputs. A reservation is not always the final settled charge; see credits and billing. If a clip completes but does not fit your brief, it does not automatically qualify for a credit return; see failed tasks and refunds.

Some completed results offer extension or additional resolution options. The source task and model determine which operations you can request. These operations are handled as separate tasks with their own credit reservations. Check the operation and displayed cost before submitting.

For Veo3.1 Fast, Lite, and Quality, Extend requires a completed original generation from the same model under your account. Rivya also needs the provider task ID for that source. It creates a continuation from the source task. An extension or resolution task cannot be extended again.

For these Veo models, the additional 1080p and 4K options require a completed original task at 720p, an older original task with no recorded resolution, or a completed Extend task. The source must belong to your account and use the same model, and Rivya needs its provider task ID. These options cannot use an original 1080p or 4K task, or a previous resolution task. Choosing a higher resolution when you first generate a clip is separate from requesting it later.

If Rivya cannot confirm whether Veo accepted the request, its task may remain in progress with credits reserved, including when no provider task ID was returned. Use the existing task record to check its status. Closing the page does not cancel it or confirm a credit return.

If the page loses its connection after submission, check History before resubmitting. A wait, timeout, or disconnected page does not prove that generation failed; another submission can incur another charge. See queue and waiting guidance. For an unresolved issue, keep the model name, task ID if shown, approximate time, and visible error for troubleshooting.

Build a larger video workflow

Use video workflows to plan the shots, files, reviews, and finishing work for a longer video. For product-specific examples, read product demo videos and prompts for product demos.