Prompt Guide
Your complete guide to prompting for AI video generation. Learn camera terminology for Text to Video and motion prompting techniques for Image to Video with Gen-4.5.
Starting with Text
A reference library of camera terminology with corresponding Text to Video prompts and their Gen-4.5 outputs. Use these examples to see how different camera terms translate into generated footage.
Shot Sizes and Framing
Macro
Detailed close up of something small to make it feel large
Extreme close up
Shows only a small detail, like just the eyes or a specific feature
Close up
Focuses tightly on the subject's face or an object
Medium
Shows from the waist up
Full
Shows the entire subject from head to toe
Wide
Shows the subject and their surroundings, full body visible
Extreme wide
Shows a vast area, often used for landscapes or to show scale
Establishing
Sets the scene by showing the location or environment
Camera Angles
Aerial
Shot from high in the air, typically from a drone or helicopter
High angle
Camera looks down on the subject from above
Low angle
Camera looks up at the subject from below
Bird's eye view
Looking straight down from above
Worm's eye view
Looking up from below
Over the shoulder
Shot from behind someone's shoulder, showing what they're looking at
POV
Point of view - shows exactly what the character sees
Composition Techniques
Leading lines
Using lines in the scene to guide the viewer's eye
Frame within frame
Using elements like doorways or windows to create a frame inside the shot
Symmetrical
Balanced composition with mirrored elements on both sides
Negative space
Empty space around the subject that draws attention to them
Camera Movements
Basic Movements
Pan
Camera rotates left or right on a fixed point
Tilt up/down
Camera rotates up or down on a fixed point
Dolly
Camera moves forward or backward on a track or wheels
Static
Camera stays completely still
Push & Pull
Push in
Camera moves closer to the subject
Pull back
Camera moves away from the subject
Truck
Camera moves left or right, parallel to the subject
Pedestal
Camera moves straight up or down vertically
Tracking & Following
Tracking
Camera follows alongside a moving subject
Orbit
Camera circles completely around the subject
Arc
Camera moves in a curved path around the subject
Crane/Jib
Camera moves up and down on a large mechanical arm
Zoom & Speed
Zoom
Lens changes focal length to make the subject appear closer or farther
Crash zoom
Very fast, dramatic zoom in or out
Whip pan
Extremely fast pan that creates motion blur
Stabilization Styles
Handheld
Camera is held by hand, creating natural shakiness
Steadicam
Stabilized handheld system that creates smooth movement while walking
Gimbal
Electronic stabilizer that keeps the camera smooth while moving
Focus Techniques
Deep focus
Everything from near to far is in sharp focus
Soft focus
Intentionally blurred or hazy look for artistic effect
Rack focus
Shifting focus from one subject to another during a shot
Shallow focus
Only a small area is in focus, the rest is blurred
Starting with an Image
Learn how to transform images into videos with Gen-4.5 using effective text prompts that describe motion, camera work, and temporal progression.
Introduction
Image to Video models transform images into videos with a text prompt. When using this generative mode, your image defines composition, subject matter, lighting, and style that guide the video.
Your prompt's role is to describe what should happen — the motion, camera work, and temporal progression you want to see using clear, direct language.

Example Prompt:
"The camera executes an aggressive, sweeping horizontal arc around the subject, followed by an extremely rapid, aggressive crash zoom that concludes with a sharp focus on the subject's eyes."
This guide builds on knowledge outlined in our Introduction to Prompting guide by introducing concepts specific to Image to Video, and is currently optimized for the newest Gen-4.5 model.
Core Prompt Elements
Text Prompt
Effective image to video prompts focus almost exclusively on motion. Rather than describing elements present in the image, use your prompt to describe the motion of the scene.
Motion Components
- •Subject action
- •Environmental motion
- •Camera motion
- •Motion style & timing
- •Direction & speed
To control individual elements from your image, refer to characters and objects with general language to isolate them and define motion.
Do I need to include every component in my prompt?
No, you do not. Omitting certain components grants the model creative freedom to produce your video. We recommend starting with a simple prompt that focuses on the most critical motion components and then adding more detail to refine as needed.
This approach to iterating helps you understand how additions and changes may affect your results.
Are there situations where I should describe visual components?
Yes, there are cases where visual descriptions can be helpful:
- •Introducing an element not present in the image
- •Dramatic changes from the starting image
- •Specifying transformation details
- •Specifying interactions between two (or more) elements
Image Prompt
Your input image acts as the first frame and provides the model with the composition, subject matter, lighting, and style information for the video.
For best results, ensure that the input image is high quality and free of visual artifacts. Visual artifacts, such as blurry hands or faces, may be intensified once your image is transformed into a video.
Prompt Structure & Organization
You don't need to follow a strict formula to generate great results. Structure and order are far less important than clearly conveying an idea and reducing ambiguity.
However, establishing an organization method can assist with effectively conveying ideas and make future iteration easier. We recommend trying this structure if you're new to generative media:
The camera [motion description] as the subject [action].
[Additional descriptions]Example Prompts:
"The camera slowly pushes in as the person scales the giant soda."
Image Input

Result

"Handheld camera: The man stands still as the crowd moves around him. He starts yelling as the camera slowly zooms out. Natural camera shake."
Image Input

Result

"Whip pan to painting of a fox. Whip pan back to the woman with a curious expression. Whip pan back to the fox painting, the fox is moving."
Image Input

Result

Advanced Techniques
Sequential Prompting
Sequential prompting provides an order of events for temporal control. This can be done through natural language, or by providing rough timestamps for an action to occur:
Natural language:
X occurs, then Y occurs. Finally, Z occurs.Timestamps:
[00:01] X occurs. [00:03] Y occurs. [00:04] Z occurs.For best results, consider if the requested sequences make sense with the selected duration. You may opt for higher durations for more complex sequences.
Creating Longer Sequences
Create longer sequences by extracting the last frame of a completed generation and using that as the image input for a new video.
To extract the last frame:
- Move the playback scrubber to the very end of the completed video
- Select "Use" from beneath the video
- Select "Use current frame"
This will load in the selected frame into the current model. Once the generation completes, you can combine both clips in a video editor to adjust timing and remove the shared frame.
Pro Tips
Combine Different Terms
Combining terms is encouraged, especially for cinematic sequences. Mix camera angles, motion, composition, and other elements to create your unique shot.
Describe Motion Phases
When prompting for dramatic motion that moves through the frame, describe what's in view or what gets revealed at each phase of the movement.
Static Camera Tips
For static shots, describe the motion that should occur within the scene. Try adding: "The camera is entirely motionless for the duration of the scene."
Focus on Motion
For Image to Video, focus almost exclusively on motion. Your image already defines composition and style — use your prompt to describe what should happen.
Start Simple
Start with a simple prompt focusing on critical motion components, then add more detail to refine. This helps you understand how changes affect results.
Check Motion Cues
Input images can contain implied motion through blur or poses. Prompting for contradicting motion may require more iteration.
Frequently Asked Questions
Can I combine different terms in my prompt?
Yes—combining terms is encouraged, especially for cinematic sequences. Gen-4.5 Text to Video has excellent prompt adherence, so you can mix complex camera angles, motion, composition, and other elements to create your unique shot.
When prompting for dramatic motion that moves through the frame, describe what's in view or what gets revealed at each phase of the movement.
How do I consistently receive scenes with a true static or motionless camera?
Video models are designed to create immersive, high-fidelity motion, which can make achieving static shots challenging for certain camera angles or scenes, most notably establishing or wide landscape shots.
To more consistently generate static camera shots, describe the motion that should occur within the scene and how elements enter and/or exit the frame.
Additionally, static shots are most consistently achievable when reinforced through natural language. As an example, you can try adding the following to your prompt:
The camera is entirely motionless for the duration of the scene, with movement only occurring from the subject.
For near-perfect generations with subtle unwanted motion, we recommend leveraging stabilization features available in most local video editors.
Why am I having challenges receiving the desired motion with a certain image?
Input images can contain implied motion through elements like motion blur, mid-action elements and poses, or directional lines. Prompting for motion that contradicts these visual cues may require more iteration to achieve your desired result.
If you're not getting the motion you want after several iterations, check your input image for implied motion cues and consider using Text/Image to Image to remove or minimize cues before generating.
Why did I receive an unwanted cut in my video?
Receiving unwanted cuts in your video may indicate that your image and prompt combination would benefit from a higher duration.
First, try increasing the duration to iterate for a seamless shot. If cuts continue to occur, check your prompt for phrasing that might indicate a cut and consider adding a prompt component like "Continuous, seamless shot" to your input.
How do I minimize camera motion for my shot?
Video models are designed to produce motion, so ensuring that you describe what motion should occur within the frame is important to receiving shots with less motion.
However, this alone may not result in a perfectly still shot. You can try adding prompt elements like the examples below to further reinforce minimal motion:
- •
The locked-off camera remains perfectly still. - •
The camera must start and end on the exact same frame to create a perfect loop. - •
Minimal subject motion only.
Using these methods to reduce camera motion and then stabilizing the shot in a video editor can help achieve the desired effect. Alternatively, consider using the Animate Frames app using the same image for both inputs for even more control.
Related Resources
Ready to Start Creating?
Head over to Runway and start experimenting with Text to Video and Image to Video using the techniques you've learned.
Go to Runway