August 26, 2026AIExplore

How to Use Runway Image to Video Generation

Animate a still as frame one with motion focused prompts, choose Gen-4 Turbo or Gen-4.5 wisely, and lock identity while you iterate.

Runway

Runway Image to Video animates an uploaded still as the first frame of a clip. Official Gen-4 help states the input image establishes composition, lighting, colors, and style, so your text prompt should focus on motion. Gen-4.5 also supports Image to Video at 12 credits per second with 2 to 10 second durations on web. Older Gen-4 and Gen-4 Turbo Image to Video options cost 12 and 5 credits per second for 5 or 10 second clips, with a 1000 character prompt limit, on web and iOS. Overview: /explore/runway.

This guide shows how to prepare stills, write motion only prompts, and use Turbo for cheap iteration before a higher quality final. Pair with image generation at /blog/how-to-use-runway-image-generation and Text to Video at /blog/how-to-use-runway-text-to-video-generation.

When Image to Video wins

Choose Image to Video when framing, wardrobe, product design, or brand color is already approved in a still. The model should not reinvent the look. Your job is to describe what moves.

Step by step Image to Video workflow

1. Prepare a clean first frame

Use a sharp still without compression artifacts, unwanted text, or warped hands if those details matter. Match the aspect ratio to your target video when possible.

Scenario:
A realistic runway workflow is being prepared for Use Runway Text to Video Generation using runway. The starting requirement is: Still checklist [ ] Subject centered or intentionally framed [ ] Lighting matches the story [ ] No accidental watermarks [ ] Aspect ratio matches delivery [ ] Export high quality PNG or JPEG. The work should be tested on a representative input first so the result can be reviewed before the same process is applied to the full project or production workload.

Objective:
Create a production-ready result for "Still checklist [ ] Subject centered or intentionally framed [ ] Lighting matches the story [ ] No accidental watermarks [ ] Aspect ratio matches delivery [ ] Export high quality PNG or JPEG" that directly supports the article use case. The output should be specific, reviewable, and reproducible rather than a generic demonstration. Keep the requested goal as the primary outcome and avoid adding unrelated features, assumptions, or unsupported capabilities.

Inputs:
Use the actual source material required for this task, together with the intended audience, destination, format, and quality requirements. Specify relevant files, text, URLs, structured data, reference assets, dimensions, language, tone, timing, model or generation settings, credentials, field mappings, or integration values when they apply. Keep secrets out of the example and use the product's supported credential or configuration mechanism.

Workflow:
1. Start with one representative input that contains the important characteristics of the real workload.
2. Configure runway specifically for the requested task and make the important settings explicit.
3. Run the first pass and inspect the result against the objective.
4. Correct only the settings or source material responsible for a failed requirement instead of changing everything at once.
5. Validate the intermediate result before passing it to the next step.
6. When the result meets the requirements, save the successful configuration so the same process can be repeated consistently.
7. If this is a multi-step workflow, verify each handoff and keep a clear fallback or review path for failures.

Requirements:
The example must use supported functionality only. Do not invent product features, pricing, limits, integrations, model names, API behavior, or unavailable settings. Preserve important source data and formatting. Validate required fields before processing, handle empty or invalid input explicitly, prevent accidental duplicate processing where relevant, and stop or route the item for review when a required step fails. For credentials, use the supported secure configuration rather than placing secrets directly in the content.

Expected output:
The final result should directly satisfy the "Still checklist [ ] Subject centered or intentionally framed [ ] Lighting matches the story [ ] No accidental watermarks [ ] Aspect ratio matches delivery [ ] Export high quality PNG or JPEG" requirement and be understandable without guessing what was supplied or configured. A successful run should produce the intended output in the requested format, with the important values and workflow decisions clear enough to reproduce the result. If the workflow can fail, the expected behavior should also make the failure visible and provide a clear next action instead of silently producing an incomplete result.

2. Write a motion focused prompt

Refer to the person or object as the subject. Describe camera move, subject action, and environmental motion. Say what should stay locked.

Scenario:
A realistic runway workflow is being prepared for Use Runway Text to Video Generation using runway. The starting requirement is: Motion prompt The camera slowly pushes in as the subject turns toward the streetlight. Rain streaks move down the frame. Keep the same color grading. Background stays soft and stable.. The work should be tested on a representative input first so the result can be reviewed before the same process is applied to the full project or production workload.

Objective:
Create a production-ready result for "Motion prompt The camera slowly pushes in as the subject turns toward the streetlight. Rain streaks move down the frame. Keep the same color grading. Background stays soft and stable." that directly supports the article use case. The output should be specific, reviewable, and reproducible rather than a generic demonstration. Keep the requested goal as the primary outcome and avoid adding unrelated features, assumptions, or unsupported capabilities.

Expected output:
The final result should directly satisfy the "Motion prompt The camera slowly pushes in as the subject turns toward the streetlight. Rain streaks move down the frame. Keep the same color grading. Background stays soft and stable." requirement and be understandable without guessing what was supplied or configured. A successful run should produce the intended output in the requested format, with the important values and workflow decisions clear enough to reproduce the result. If the workflow can fail, the expected behavior should also make the failure visible and provide a clear next action instead of silently producing an incomplete result.

3. Pick model and duration

Draft on Gen-4 Turbo at 5 credits per second when that mode fits. Move to Gen-4 or Gen-4.5 at 12 credits per second when motion is right and you need higher quality. Gen-4 family durations are 5 or 10 seconds; Gen-4.5 allows 2 to 10 seconds.

Scenario:
A realistic runway workflow is being prepared for Use Runway Text to Video Generation using runway. The starting requirement is: Cost sketch Turbo 5s = 25 credits Turbo 10s = 50 credits Gen-4 or Gen-4.5 5s = 60 credits Gen-4 or Gen-4.5 10s = 120 credits Confirm live rates in official help before budgeting. The work should be tested on a representative input first so the result can be reviewed before the same process is applied to the full project or production workload.

Objective:
Create a production-ready result for "Cost sketch Turbo 5s = 25 credits Turbo 10s = 50 credits Gen-4 or Gen-4.5 5s = 60 credits Gen-4 or Gen-4.5 10s = 120 credits Confirm live rates in official help before budgeting" that directly supports the article use case. The output should be specific, reviewable, and reproducible rather than a generic demonstration. Keep the requested goal as the primary outcome and avoid adding unrelated features, assumptions, or unsupported capabilities.

Expected output:
The final result should directly satisfy the "Cost sketch Turbo 5s = 25 credits Turbo 10s = 50 credits Gen-4 or Gen-4.5 5s = 60 credits Gen-4 or Gen-4.5 10s = 120 credits Confirm live rates in official help before budgeting" requirement and be understandable without guessing what was supplied or configured. A successful run should produce the intended output in the requested format, with the important values and workflow decisions clear enough to reproduce the result. If the workflow can fail, the expected behavior should also make the failure visible and provide a clear next action instead of silently producing an incomplete result.

4. Diagnose failures by category

If identity drifts, simplify motion and strengthen locks. If flicker appears, reduce environmental motion. If camera is wild, request a locked camera and one subject move only.

Scenario:
A realistic runway workflow is being prepared for Use Runway Text to Video Generation using runway. The starting requirement is: Diagnosis Identity drift → softer motion + keep subject identity Background swim → keep background static Too much energy → one camera move only Artifact from still → clean the input image first. The work should be tested on a representative input first so the result can be reviewed before the same process is applied to the full project or production workload.

Objective:
Create a production-ready result for "Diagnosis Identity drift → softer motion + keep subject identity Background swim → keep background static Too much energy → one camera move only Artifact from still → clean the input image first" that directly supports the article use case. The output should be specific, reviewable, and reproducible rather than a generic demonstration. Keep the requested goal as the primary outcome and avoid adding unrelated features, assumptions, or unsupported capabilities.

Expected output:
The final result should directly satisfy the "Diagnosis Identity drift → softer motion + keep subject identity Background swim → keep background static Too much energy → one camera move only Artifact from still → clean the input image first" requirement and be understandable without guessing what was supplied or configured. A successful run should produce the intended output in the requested format, with the important values and workflow decisions clear enough to reproduce the result. If the workflow can fail, the expected behavior should also make the failure visible and provide a clear next action instead of silently producing an incomplete result.

Practical Image to Video use cases

Portrait push in

Scenario:
A realistic runway workflow is being prepared for Use Runway Text to Video Generation using runway. The starting requirement is: [upload portrait] Slow push in. The subject blinks once and softens their expression. Keep wardrobe and background identical. Locked color grade.. The work should be tested on a representative input first so the result can be reviewed before the same process is applied to the full project or production workload.

Objective:
Create a production-ready result for "[upload portrait] Slow push in. The subject blinks once and softens their expression. Keep wardrobe and background identical. Locked color grade." that directly supports the article use case. The output should be specific, reviewable, and reproducible rather than a generic demonstration. Keep the requested goal as the primary outcome and avoid adding unrelated features, assumptions, or unsupported capabilities.

Expected output:
The final result should directly satisfy the "[upload portrait] Slow push in. The subject blinks once and softens their expression. Keep wardrobe and background identical. Locked color grade." requirement and be understandable without guessing what was supplied or configured. A successful run should produce the intended output in the requested format, with the important values and workflow decisions clear enough to reproduce the result. If the workflow can fail, the expected behavior should also make the failure visible and provide a clear next action instead of silently producing an incomplete result.

Product turntable

Scenario:
A realistic runway workflow is being prepared for Use Runway Text to Video Generation using runway. The starting requirement is: [upload product on white] Smooth turntable rotation. Camera locked. Constant soft studio light. No new props. No text.. The work should be tested on a representative input first so the result can be reviewed before the same process is applied to the full project or production workload.

Objective:
Create a production-ready result for "[upload product on white] Smooth turntable rotation. Camera locked. Constant soft studio light. No new props. No text." that directly supports the article use case. The output should be specific, reviewable, and reproducible rather than a generic demonstration. Keep the requested goal as the primary outcome and avoid adding unrelated features, assumptions, or unsupported capabilities.

Expected output:
The final result should directly satisfy the "[upload product on white] Smooth turntable rotation. Camera locked. Constant soft studio light. No new props. No text." requirement and be understandable without guessing what was supplied or configured. A successful run should produce the intended output in the requested format, with the important values and workflow decisions clear enough to reproduce the result. If the workflow can fail, the expected behavior should also make the failure visible and provide a clear next action instead of silently producing an incomplete result.

Forest atmosphere

Scenario:
A realistic runway workflow is being prepared for Use Runway Text to Video Generation using runway. The starting requirement is: [upload forest still] Camera locked. Only leaves and distant fog drift. Subject remains still. Soft overcast light unchanged.. The work should be tested on a representative input first so the result can be reviewed before the same process is applied to the full project or production workload.

Objective:
Create a production-ready result for "[upload forest still] Camera locked. Only leaves and distant fog drift. Subject remains still. Soft overcast light unchanged." that directly supports the article use case. The output should be specific, reviewable, and reproducible rather than a generic demonstration. Keep the requested goal as the primary outcome and avoid adding unrelated features, assumptions, or unsupported capabilities.

Expected output:
The final result should directly satisfy the "[upload forest still] Camera locked. Only leaves and distant fog drift. Subject remains still. Soft overcast light unchanged." requirement and be understandable without guessing what was supplied or configured. A successful run should produce the intended output in the requested format, with the important values and workflow decisions clear enough to reproduce the result. If the workflow can fail, the expected behavior should also make the failure visible and provide a clear next action instead of silently producing an incomplete result.

Fashion fabric move

Scenario:
A realistic runway workflow is being prepared for Use Runway Text to Video Generation using runway. The starting requirement is: [upload fashion midshot] Handheld subtle shake. Fabric ripples in a light breeze. Subject stands mostly still. Keep makeup and color grade.. The work should be tested on a representative input first so the result can be reviewed before the same process is applied to the full project or production workload.

Objective:
Create a production-ready result for "[upload fashion midshot] Handheld subtle shake. Fabric ripples in a light breeze. Subject stands mostly still. Keep makeup and color grade." that directly supports the article use case. The output should be specific, reviewable, and reproducible rather than a generic demonstration. Keep the requested goal as the primary outcome and avoid adding unrelated features, assumptions, or unsupported capabilities.

Expected output:
The final result should directly satisfy the "[upload fashion midshot] Handheld subtle shake. Fabric ripples in a light breeze. Subject stands mostly still. Keep makeup and color grade." requirement and be understandable without guessing what was supplied or configured. A successful run should produce the intended output in the requested format, with the important values and workflow decisions clear enough to reproduce the result. If the workflow can fail, the expected behavior should also make the failure visible and provide a clear next action instead of silently producing an incomplete result.

Food simmer

Scenario:
A realistic runway workflow is being prepared for Use Runway Text to Video Generation using runway. The starting requirement is: [upload bowl still] Camera locked. Steam rises continuously. Broth surface shows soft ripples. No spoon motion unless present in the still.. The work should be tested on a representative input first so the result can be reviewed before the same process is applied to the full project or production workload.

Objective:
Create a production-ready result for "[upload bowl still] Camera locked. Steam rises continuously. Broth surface shows soft ripples. No spoon motion unless present in the still." that directly supports the article use case. The output should be specific, reviewable, and reproducible rather than a generic demonstration. Keep the requested goal as the primary outcome and avoid adding unrelated features, assumptions, or unsupported capabilities.

Expected output:
The final result should directly satisfy the "[upload bowl still] Camera locked. Steam rises continuously. Broth surface shows soft ripples. No spoon motion unless present in the still." requirement and be understandable without guessing what was supplied or configured. A successful run should produce the intended output in the requested format, with the important values and workflow decisions clear enough to reproduce the result. If the workflow can fail, the expected behavior should also make the failure visible and provide a clear next action instead of silently producing an incomplete result.

Car teaser

Scenario:
A realistic runway workflow is being prepared for Use Runway Text to Video Generation using runway. The starting requirement is: [upload coupe still] Slow orbit around the car. Reflections crawl across the body. Garage lights stay fixed. No brand marks added.. The work should be tested on a representative input first so the result can be reviewed before the same process is applied to the full project or production workload.

Objective:
Create a production-ready result for "[upload coupe still] Slow orbit around the car. Reflections crawl across the body. Garage lights stay fixed. No brand marks added." that directly supports the article use case. The output should be specific, reviewable, and reproducible rather than a generic demonstration. Keep the requested goal as the primary outcome and avoid adding unrelated features, assumptions, or unsupported capabilities.

Expected output:
The final result should directly satisfy the "[upload coupe still] Slow orbit around the car. Reflections crawl across the body. Garage lights stay fixed. No brand marks added." requirement and be understandable without guessing what was supplied or configured. A successful run should produce the intended output in the requested format, with the important values and workflow decisions clear enough to reproduce the result. If the workflow can fail, the expected behavior should also make the failure visible and provide a clear next action instead of silently producing an incomplete result.

Architecture interior

Scenario:
A realistic runway workflow is being prepared for Use Runway Text to Video Generation using runway. The starting requirement is: [upload lobby still] Gentle dolly forward down the hall. People remain soft background motion only if already visible. Keep architecture sharp.. The work should be tested on a representative input first so the result can be reviewed before the same process is applied to the full project or production workload.

Objective:
Create a production-ready result for "[upload lobby still] Gentle dolly forward down the hall. People remain soft background motion only if already visible. Keep architecture sharp." that directly supports the article use case. The output should be specific, reviewable, and reproducible rather than a generic demonstration. Keep the requested goal as the primary outcome and avoid adding unrelated features, assumptions, or unsupported capabilities.

Expected output:
The final result should directly satisfy the "[upload lobby still] Gentle dolly forward down the hall. People remain soft background motion only if already visible. Keep architecture sharp." requirement and be understandable without guessing what was supplied or configured. A successful run should produce the intended output in the requested format, with the important values and workflow decisions clear enough to reproduce the result. If the workflow can fail, the expected behavior should also make the failure visible and provide a clear next action instead of silently producing an incomplete result.

UI mock ambience

Scenario:
A realistic runway workflow is being prepared for Use Runway Text to Video Generation using runway. The starting requirement is: [upload device still] Camera locked. Only a subtle screen light flicker. Device body stays perfectly still. No new UI text.. The work should be tested on a representative input first so the result can be reviewed before the same process is applied to the full project or production workload.

Objective:
Create a production-ready result for "[upload device still] Camera locked. Only a subtle screen light flicker. Device body stays perfectly still. No new UI text." that directly supports the article use case. The output should be specific, reviewable, and reproducible rather than a generic demonstration. Keep the requested goal as the primary outcome and avoid adding unrelated features, assumptions, or unsupported capabilities.

Expected output:
The final result should directly satisfy the "[upload device still] Camera locked. Only a subtle screen light flicker. Device body stays perfectly still. No new UI text." requirement and be understandable without guessing what was supplied or configured. A successful run should produce the intended output in the requested format, with the important values and workflow decisions clear enough to reproduce the result. If the workflow can fail, the expected behavior should also make the failure visible and provide a clear next action instead of silently producing an incomplete result.

Sports freeze to motion

Scenario:
A realistic runway workflow is being prepared for Use Runway Text to Video Generation using runway. The starting requirement is: [upload athlete still] Subject begins a slow follow through of the swing. Camera tracks gently with the motion. Keep jersey details stable.. The work should be tested on a representative input first so the result can be reviewed before the same process is applied to the full project or production workload.

Objective:
Create a production-ready result for "[upload athlete still] Subject begins a slow follow through of the swing. Camera tracks gently with the motion. Keep jersey details stable." that directly supports the article use case. The output should be specific, reviewable, and reproducible rather than a generic demonstration. Keep the requested goal as the primary outcome and avoid adding unrelated features, assumptions, or unsupported capabilities.

Expected output:
The final result should directly satisfy the "[upload athlete still] Subject begins a slow follow through of the swing. Camera tracks gently with the motion. Keep jersey details stable." requirement and be understandable without guessing what was supplied or configured. A successful run should produce the intended output in the requested format, with the important values and workflow decisions clear enough to reproduce the result. If the workflow can fail, the expected behavior should also make the failure visible and provide a clear next action instead of silently producing an incomplete result.

Kids illustration calm

Scenario:
A realistic runway workflow is being prepared for Use Runway Text to Video Generation using runway. The starting requirement is: [upload storybook still] Soft parallax: foreground grass sways, kite string drifts. Camera holds. No new characters.. The work should be tested on a representative input first so the result can be reviewed before the same process is applied to the full project or production workload.

Objective:
Create a production-ready result for "[upload storybook still] Soft parallax: foreground grass sways, kite string drifts. Camera holds. No new characters." that directly supports the article use case. The output should be specific, reviewable, and reproducible rather than a generic demonstration. Keep the requested goal as the primary outcome and avoid adding unrelated features, assumptions, or unsupported capabilities.

Expected output:
The final result should directly satisfy the "[upload storybook still] Soft parallax: foreground grass sways, kite string drifts. Camera holds. No new characters." requirement and be understandable without guessing what was supplied or configured. A successful run should produce the intended output in the requested format, with the important values and workflow decisions clear enough to reproduce the result. If the workflow can fail, the expected behavior should also make the failure visible and provide a clear next action instead of silently producing an incomplete result.

More prompts

Scenario:
A realistic runway workflow is being prepared for Use Runway Text to Video Generation using runway. The starting requirement is: Prompt: crowd blur [upload street still] Subject stands still. Crowd flows around them. Handheld natural shake. Keep exposure locked.. The work should be tested on a representative input first so the result can be reviewed before the same process is applied to the full project or production workload.

Objective:
Create a production-ready result for "Prompt: crowd blur [upload street still] Subject stands still. Crowd flows around them. Handheld natural shake. Keep exposure locked." that directly supports the article use case. The output should be specific, reviewable, and reproducible rather than a generic demonstration. Keep the requested goal as the primary outcome and avoid adding unrelated features, assumptions, or unsupported capabilities.

Expected output:
The final result should directly satisfy the "Prompt: crowd blur [upload street still] Subject stands still. Crowd flows around them. Handheld natural shake. Keep exposure locked." requirement and be understandable without guessing what was supplied or configured. A successful run should produce the intended output in the requested format, with the important values and workflow decisions clear enough to reproduce the result. If the workflow can fail, the expected behavior should also make the failure visible and provide a clear next action instead of silently producing an incomplete result.

Scenario:
A realistic runway workflow is being prepared for Use Runway Text to Video Generation using runway. The starting requirement is: Prompt: candle light [upload table still] Camera locked. Candle flame flickers. Soft shadow dance on the wall. Objects otherwise still.. The work should be tested on a representative input first so the result can be reviewed before the same process is applied to the full project or production workload.

Objective:
Create a production-ready result for "Prompt: candle light [upload table still] Camera locked. Candle flame flickers. Soft shadow dance on the wall. Objects otherwise still." that directly supports the article use case. The output should be specific, reviewable, and reproducible rather than a generic demonstration. Keep the requested goal as the primary outcome and avoid adding unrelated features, assumptions, or unsupported capabilities.

Expected output:
The final result should directly satisfy the "Prompt: candle light [upload table still] Camera locked. Candle flame flickers. Soft shadow dance on the wall. Objects otherwise still." requirement and be understandable without guessing what was supplied or configured. A successful run should produce the intended output in the requested format, with the important values and workflow decisions clear enough to reproduce the result. If the workflow can fail, the expected behavior should also make the failure visible and provide a clear next action instead of silently producing an incomplete result.

Scenario:
A realistic runway workflow is being prepared for Use Runway Text to Video Generation using runway. The starting requirement is: Prompt: train window [upload passenger still] Camera locked on subject. Landscape streaks past the window. Subject remains calm and mostly still.. The work should be tested on a representative input first so the result can be reviewed before the same process is applied to the full project or production workload.

Objective:
Create a production-ready result for "Prompt: train window [upload passenger still] Camera locked on subject. Landscape streaks past the window. Subject remains calm and mostly still." that directly supports the article use case. The output should be specific, reviewable, and reproducible rather than a generic demonstration. Keep the requested goal as the primary outcome and avoid adding unrelated features, assumptions, or unsupported capabilities.

Expected output:
The final result should directly satisfy the "Prompt: train window [upload passenger still] Camera locked on subject. Landscape streaks past the window. Subject remains calm and mostly still." requirement and be understandable without guessing what was supplied or configured. A successful run should produce the intended output in the requested format, with the important values and workflow decisions clear enough to reproduce the result. If the workflow can fail, the expected behavior should also make the failure visible and provide a clear next action instead of silently producing an incomplete result.

Scenario:
A realistic runway workflow is being prepared for Use Runway Text to Video Generation using runway. The starting requirement is: Prompt: jewelry sparkle [upload macro jewelry] Slow tilt revealing facets. Tiny specular sparkles travel across metal. Keep stones sharp.. The work should be tested on a representative input first so the result can be reviewed before the same process is applied to the full project or production workload.

Objective:
Create a production-ready result for "Prompt: jewelry sparkle [upload macro jewelry] Slow tilt revealing facets. Tiny specular sparkles travel across metal. Keep stones sharp." that directly supports the article use case. The output should be specific, reviewable, and reproducible rather than a generic demonstration. Keep the requested goal as the primary outcome and avoid adding unrelated features, assumptions, or unsupported capabilities.

Expected output:
The final result should directly satisfy the "Prompt: jewelry sparkle [upload macro jewelry] Slow tilt revealing facets. Tiny specular sparkles travel across metal. Keep stones sharp." requirement and be understandable without guessing what was supplied or configured. A successful run should produce the intended output in the requested format, with the important values and workflow decisions clear enough to reproduce the result. If the workflow can fail, the expected behavior should also make the failure visible and provide a clear next action instead of silently producing an incomplete result.

Scenario:
A realistic runway workflow is being prepared for Use Runway Text to Video Generation using runway. The starting requirement is: Prompt: last frame continue Use Current Frame from a good take as the next Image to Video input. Prompt only the next motion beat.. The work should be tested on a representative input first so the result can be reviewed before the same process is applied to the full project or production workload.

Objective:
Create a production-ready result for "Prompt: last frame continue Use Current Frame from a good take as the next Image to Video input. Prompt only the next motion beat." that directly supports the article use case. The output should be specific, reviewable, and reproducible rather than a generic demonstration. Keep the requested goal as the primary outcome and avoid adding unrelated features, assumptions, or unsupported capabilities.

Expected output:
The final result should directly satisfy the "Prompt: last frame continue Use Current Frame from a good take as the next Image to Video input. Prompt only the next motion beat." requirement and be understandable without guessing what was supplied or configured. A successful run should produce the intended output in the requested format, with the important values and workflow decisions clear enough to reproduce the result. If the workflow can fail, the expected behavior should also make the failure visible and provide a clear next action instead of silently producing an incomplete result.

Tips and verification

Do not re describe the entire image in text
One primary motion per test
Positive locks beat long negative lists
Clean stills before spending video credits
Confirm Gen-4.5 vs Gen-4 Turbo availability on your plan and device
Remember app credits differ from API credits

Keep a short shot list beside your Runway session. Note model, duration, aspect ratio, and the one motion change you will try next. That habit saves credits when you iterate.

When a generation pauses or a plan limit appears, confirm your plan and remaining credits in the dashboard instead of guessing. Official Free plan help notes watermarks and a one time credit deposit.

Treat every clip as a draft until you review subject identity, flicker, and unwanted text. Export only after a full playback, not a frozen thumbnail.

If you collaborate, store winning prompts on a shared page with the seed when available. Reuse the prompt skeleton and change one variable at a time.

Match delivery early. A 9:16 social cut is harder to rescue from a 16:9 master than starting in the correct ratio.

Separate exploration from finals. Draft on lower cost models when they fit the mode, then spend Gen-4.5 credits once motion and framing are locked.

For client work, keep a verification note: no invented logos, no trademarked characters, and no claims the footage cannot support.

Close each session by archiving the best still or last frame for the next shot. Continuity across clips beats regenerating from memory.