Rivya Image Workflows: Plan, Compare, and Finish a Set

Use this guide to take a set of images from a brief to approved files. For uploading, generation controls, and result previews, use the Image Studio guide.

Define the set before generating

Write down the placements, facts that must remain accurate, and what may change between images. For example, a bottle campaign might need a square product image, a wide website image with space for a heading, and a vertical social image. These are three deliverables to review separately, not a batch that Rivya automatically assembles.

Keep the bottle's real shape, color, and label as acceptance criteria. Background, lighting, and framing may vary. Do not add unverified material, capacity, or performance claims to make the brief sound complete.

Choose inputs and an available model

Compare the image overview and model directory, checking supported inputs, output settings, and estimated credits. A familiar model name does not establish suitability; check current availability before opening its Studio. Sign in to upload or submit work.

If the product must follow a real object, choose a model that accepts the required images. Give each reference a purpose, such as product appearance or composition. References guide generation; they do not guarantee exact geometry, lettering, or consistency across a set. See image references and the model-specific upload limits.

Test one composition, then make the remaining images

1. Pick one representative placement and define its acceptance criteria before spending credits.

2. Write a focused request, such as: “Center the bottle from the product reference on a light gray background. Leave space above for a heading. Add no props.” This is an illustrative brief, not a tested output or a promise of exact reproduction. Use prompt-writing basics to clarify ambiguous instructions.

3. Check the model's supported aspect ratio, resolution, attached references, and estimated cost; then submit one task. Only choose a lower-cost setting if it can answer the question you are testing. Lower cost does not guarantee useful results or lower total spending.

4. Review the image before adapting the approved direction to the other placements. Check each new form and result; a new ratio or reference can change the composition and product details.

Decide what to change and when to stop

Keep a short note of what changed between attempts. Changing the model, prompt, and references together makes the cause of a difference harder to assess. Higher resolution alone does not correct false product details or an unsuitable composition.

Set a credit budget and stop to reassess when it is reached. Every new generation or finishing task has its own cost; check credit billing. A successfully generated image that you dislike is not a failed task with an automatic refund; see failures and refunds.

Finish and keep the approved files

Use background removal, upscaling, or layer separation only when the operation fits the remaining task. Inspect edges, text, shadows, and altered details at the intended display size. Separate layers need review and assembly in an external editor; these operations do not verify product claims.

Find submitted tasks in History, then download accepted results. Keep the approved brief, model, settings, references, and final files yourself. Saved sessions are not a complete editable project archive or a guarantee of permanent file access.

For motion, continue with an accepted still and a compatible model using video workflows. Review the destination's input limits and settings. This starts a separate task; it does not automatically animate or assemble your image set.

Apply the workflow to a specific placement

Use the product-photo prompt guide for the product brief, the landing-page image guide for layout and text space, and the advertising image guide for an ad-specific review. Keep the same verified product facts across all three.