# Prompting best practices for Amazon Nova content creation models
Prompting content creation models

**Note**  
This documentation is for Amazon Nova Version 1. Amazon Nova 2 is now available with new models and enhanced capabilities. New features and documentation updates are published in the Amazon Nova 2 User Guide. For information on prompt engineering for Amazon Nova 2, visit [Prompt engineering guide](https://docs.aws.amazon.com/nova/latest/nova2-userguide/prompt-engineering-guide.html).

Amazon Nova consists of two creative content generation models, Amazon Nova Canvas and Amazon Nova Reel. The following guidance addresses the image and video generation models. For guidance on multimodal understanding models, [Prompting best practices for Amazon Nova understanding models](prompting.md).

**Topics**
+ [

# Amazon Nova Canvas prompting best practices
](prompting-image-generation.md)
+ [

# Amazon Nova Reel prompting best practices
](prompting-video-generation.md)

# Amazon Nova Canvas prompting best practices
Prompting Amazon Nova Canvas

Prompting for image generation models differs from prompting for large language models (LLMs). Image generation models do not have the ability to reason or interpret explicit commands. Therefore, it's best to phrase your prompt as if it were an image caption rather than a command or conversation. You might want to include details about the subject, action, environment, lighting, style, and camera position.

When writing an image generation prompt, be mindful of the following requirements and best practices:
+ Prompts must be no longer than 1024 characters. For very long prompts, place the least important details of your prompt near the end.
+ Do not use negation words like *"no"*, *"not"*, *"without"*, and so on in your prompt. The model doesn't understand negation in a prompt and attempting to use negation will result in the opposite of what you intend. For example, a prompt such as *"a fruit basket with no bananas"* will actually signal the model to include bananas. Instead, you can use a negative prompt, via the `negativeText` parameter, to specify any objects or characteristics that you want to exclude from the image. For example *"bananas"*.
+ As with prompts, omit negation words from your negative prompts.
+ When the output you get from a prompt is close to what you want but not quite perfect, try the following techniques one at a time in turn to refine your result:
  + Using a consistent `seed` value, make small changes to your prompt or negative prompt and re-run the prompt. This allows you to better understand how your prompt wording affects the output, allowing you to iteratively improve your results in a controlled way.
  + Once the prompt has been refined to your liking, generate more variations using the same prompt but a different `seed` value. It is often useful to generate multiple variations of an image by running the sample prompt with different seeds in order to find that perfect output image.

An effective prompt often includes short descriptions of...

1. the subject

1. the environment

1. (optional) the position or pose of the subject

1. (optional) lighting description

1. (optional) camera position/framing

1. (optional) the visual style or medium ("photo", "illustration", "painting", and so on)

## Example 1: Stock photo


**Prompt:** realistic editorial photo of female teacher standing at a blackboard with a warm smile

**Negative Prompt:** crossed arms

![\[editorial photo of female teacher standing at a blackboard with a warm smile\]](http://docs.aws.amazon.com/nova/latest/userguide/images/example1.png)


## Example 2: Story illustration


**Prompt:** whimsical and ethereal soft-shaded story illustration: A woman in a large hat stands at the ship's railing looking out across the ocean

**Negative Prompt:** clouds, waves

![\[whimsical and ethereal soft-shaded story illustration: A woman in a large hat stands at the ship's railing looking out across the ocean\]](http://docs.aws.amazon.com/nova/latest/userguide/images/simple-image-output-1.png)


## Example 3: Pre-visualization for TV and film production


**Prompt:** drone view of a dark river winding through a stark Iceland landscape, cinematic quality

![\[drone view of a dark river winding through a stark Iceland landscape, cinematic quality\]](http://docs.aws.amazon.com/nova/latest/userguide/images/previs.png)


## Example 4: Fashion or editorial content


**Prompt:** A cool looking stylish man in an orange jacket, dark skin, wearing reflective glasses. Shot from slightly low angle, face and chest in view, aqua blue sleek building shapes in background.

![\[A cool looking stylish man in an orange jacket, dark skin, wearing reflective glasses. Shot from slightly low angle, face and chest in view, aqua blue sleek building shapes in background.\]](http://docs.aws.amazon.com/nova/latest/userguide/images/output.png)


**Topics**
+ [

# Negative prompts
](prompting-image-negative.md)
+ [

# Mask prompts
](prompting-image-masks.md)
+ [

# Inpainting prompts
](prompting-image-inpainting.md)
+ [

# Outpainting prompts
](prompting-image-outpainting.md)

# Negative prompts


Negative prompts, represented by the `negativeText` parameter, can be surprisingly useful. Use negative prompts to exclude objects or style characteristics that might otherwise naturally occur as a result of your main prompt. Here is an example.

**Prompt:** *"whimsical and ethereal soft-shaded story illustration: A woman in a large hat stands at the ship's railing looking out across the ocean"*

**Without a negative prompt**

![\[whimsical and ethereal soft-shaded story illustration: A woman in a large hat stands at the ship's railing looking out across the ocean\]](http://docs.aws.amazon.com/nova/latest/userguide/images/image_1.png)


**With the negative prompt** "waves, clouds"

![\[Previous image with the negative prompt "waves, clouds"\]](http://docs.aws.amazon.com/nova/latest/userguide/images/image_1(1).png)


# Mask prompts


Mask prompts are used in editing operations. A mask prompt allows you to use natural language to describe the elements within an image that you want to change (in the case of inpainting) or to remain untouched (in the case of outpainting). You pass a mask prompt as part of your request using the `maskPrompt` parameter. Below are some examples that visualize the result of a mask prompt. The masked area is colored in dark blue.

**Mask Prompt: "dog"**

![\[A dog\]](http://docs.aws.amazon.com/nova/latest/userguide/images/Screenshot1.png)


**maskPrompt: "dog"**

![\[A dog\]](http://docs.aws.amazon.com/nova/latest/userguide/images/Screenshot3.png)


**Mask Prompt: "dog in a bucket"**

![\[A dog in a bucket\]](http://docs.aws.amazon.com/nova/latest/userguide/images/Screenshot2.png)


**maskPrompt: "black dog"**

![\[A black dog\]](http://docs.aws.amazon.com/nova/latest/userguide/images/Screenshot4.png)


# Inpainting prompts


Inpainting is an editing operation that can be used to add, remove, or replace elements within an image. Inpainting requires an input image and either a natural language mask prompt (`maskPrompt`) or a user-provided mask image (`maskImage`) to define which parts of an image to change.

## Example 1: Removing elements from an image


To remove an element from an image, provide a mask that fully encompasses the thing you want to remove, and omit the `text` parameter from your request. This signals to the model to remove that element.

**Input Image**

![\[Three pots\]](http://docs.aws.amazon.com/nova/latest/userguide/images/three_pots.jpg)


**Mask Prompt**

"flowers in pots"

**Result**

![\[Scene with no pots\]](http://docs.aws.amazon.com/nova/latest/userguide/images/remove-with-prompt.png)


## Example 2: Adding elements to an image


To add an element to an image, use a mask that defines the bounds of the area where you want the element to be added and a text prompt that describes what you want the *whole* image to look like after the edit. It is usually more effective to use a mask image for this, but you may use a mask prompt instead.

The following example uses a `text` value of *"a garden gnome under a table in a greenhouse".*

**Input Image**

![\[Three pots\]](http://docs.aws.amazon.com/nova/latest/userguide/images/three_pots.jpg)


**Mask Image**

![\[Mask image\]](http://docs.aws.amazon.com/nova/latest/userguide/images/three_pots-add_mask_INVERTED.png)


**Result**

![\[New element added to the mask location\]](http://docs.aws.amazon.com/nova/latest/userguide/images/add-with-mask-image-1.png)


## Example 3: Replacing elements in an image


You can replace one element with a new one using inpainting. A common way to achieve this is to use a mask prompt that describes the thing you want to replace. When using this approach, the outline of the new content will closely match the outline of the element which it is replacing. If this is not what you desire, create a mask image that fully encompasses the element you want to replace but doesn't adhere directly to its contours.

The following example uses a `text` value of *"a palm tree graphic"* and a `negativeText` value of *"colorful"*.

**Input Image**

![\[Reference image\]](http://docs.aws.amazon.com/nova/latest/userguide/images/ref-img-seed-1.png)


**Mask Prompt**

*"dog"*

**Result**

![\[Inpainted image\]](http://docs.aws.amazon.com/nova/latest/userguide/images/ref-inpainted-1.png)


# Outpainting prompts


Outpainting is used to replace the background of an image. For best results, outpainting prompts should describe what you would like the *whole* image to look like, including the parts of the image that will not be changed.

The following example uses a `text` value of *"a coffee maker in a sparse stylish kitchen, a single plate of pastries next to the coffee maker, a single cup of coffee".*

**Input Image**

![\[Amazon coffee maker\]](http://docs.aws.amazon.com/nova/latest/userguide/images/amazon-coffee-maker-1.png)


**Mask Prompt**: *"coffee maker"*

**Result**

![\[Background replacement image\]](http://docs.aws.amazon.com/nova/latest/userguide/images/background-replacement-mask-prompt-example-1.png)


Here is another example that uses a `text` value of *"detailed photo of a flower pot sitting on an outdoor potting bench".*

**Input Image**

![\[Three pots\]](http://docs.aws.amazon.com/nova/latest/userguide/images/three_pots.jpg)


**Mask Image**

![\[mask image\]](http://docs.aws.amazon.com/nova/latest/userguide/images/three_pots-remove_mask_INVERTED.png)


**Result**

![\[Mask item moved to a new background\]](http://docs.aws.amazon.com/nova/latest/userguide/images/potted.png)


# Amazon Nova Reel prompting best practices
Prompting Amazon Nova Reel

Prompting for video generation models differs from prompting for large language models (LLMs). Video generation models do not have the ability to reason or interpret explicit commands. Therefore, it's best to phrase your prompt as if it were an image caption or summary of the video rather than a command or conversation. You may want to include details about the subject, action, environment, lighting, style, and camera motion.

When writing a video generation prompt, be mindful of the following requirements and best practices:
+ Generally, prompts must be no longer than 512 characters.
+ For videos longer than six seconds created from a single prompt, your prompt can be up to 4000 characters. In this case, we recommend that you write a longer, more comprehensive prompt. This will better guide the model towards your desired outcome.
+ If you'd like to influence camera movement, you will get the best results if you place camera movement descriptions at the start or end of your prompt.
+ Do not use negation words like *"no"*, *"not"*, *"without"*, and so on. The model doesn't understand negation in a prompt and attempting to use negation will result in the opposite of what you intend. For example, a prompt that includes *"pan across a fruit basket with no bananas"* will actually signal to the model to include bananas.
+ When the output you get from a prompt is close to what you want but not quite perfect, try the following techniques one at a time in turn to refine your result:
  + Using a consistent `seed` value, make small changes to your prompt and re-run the prompt. This allows you to better understand how your prompt wording affects the output, allowing you to iteratively improve your results in a controlled way.
  + Once the prompt has been refined to your liking, generate more variations using the same prompt but a different `seed` value. It is often useful to generate multiple variations of an video by running the sample prompt with different seeds in order to find that perfect video clip.

When using the storyboard, you can include a prompt for each six second interval. Each prompt on the storyboard must follow the preceding requirements and guidelines

**Topics**
+ [

## Example video generation prompts
](#prompting-video-examples)
+ [

# Image-based video generation prompts
](prompting-video-image-prompts.md)
+ [

# Camera controls
](prompting-video-camera-control.md)

## Example video generation prompts


Here are some example prompts to get you started with video generation.

### Photorealistic video of a cheeseburger


**Prompt:** *"Cinematic dolly shot of a juicy cheeseburger with melting cheese, fries, and a condensation-covered cola on a worn diner table. Natural lighting, visible steam and droplets. 4k, photorealistic, shallow depth of field"*

### Cinematic shot of a salad


**Prompt:** *"Arc shot on a salad with dressing, olives and other vegetables; 4k; Cinematic;"*

### Motorcycle ride through a forest


**Prompt**: *"First person view of a motorcycle riding through the forest road."*

### Large seashell at the beach


**Prompt:** *"Closeup of a large seashell in the sand. Gentle waves flow around the shell. Camera zoom in."*

### Clothes drying on a line


**Prompt:** *"Clothes hanging on a thread to dry, windy; sunny day; 4k; Cinematic; highest quality;"*

### Dolly shot of a man


**Prompt:** *"Slow cam of a man middle age; 4k; Cinematic; in a sunny day; peaceful; highest quality; dolly in;"*

### A mushroom drinking coffee


**Prompt:** *"A mushroom drinking a cup of coffee while sitting on a couch, photorealistic."*

# Image-based video generation prompts
Image-based prompts

Image-based prompts are a great way to gain more control over your video output and to streamline your video generation workflow. By providing a starting frame that reflects the exact content, framing, and visual style you would like, you greatly improve the likelihood that your generated video will meet your needs. For best results, use the Amazon Nova Canvas model to create your input image. Amazon Nova Reel and Amazon Nova Canvas have been designed to work well together.

There are two primary approaches you can leverage when using images as input for video generation.

If your goal is to add camera motion to bring a static image to life, you can rely on the image itself to convey the subject and visual style while using the text prompt to describe only the camera motion. (See [Camera controls](prompting-video-camera-control.md) for more on prompting camera movement.)

**Example of prompting with camera motion only**

**Input image**

![\[Rocky coastal landscape with rugged cliffs, blue ocean, and distant mountains.\]](http://docs.aws.amazon.com/nova/latest/userguide/images/sample-frame-1.png)


**Prompt**: *"dolly forward"*

However, if you desire to have your subjects perform a particular action or would like to influence other changes that play out over time, it's best to describe the subjects, actions, and changes in detail. Remember to phrase the prompt as a summary rather than a command.

**Input Image**

![\[White dog with brown patches wearing a colorful Christmas light necklace on a plaid couch.\]](http://docs.aws.amazon.com/nova/latest/userguide/images/sample-frame-2.png)


**Prompt**: *"dynamic handheld shot: the dog looks to the left as colored holiday lights on its body blink rhythmically"*

For videos longer than six seconds, you can only include prompt images if you use the storyboard. You can include an optional input image and prompt to guide the creation of each six second shot of the video. However, you don't need to include inputs for every six second shot.

# Camera controls


The follow terminology will be useful in achieving specific camera shots, framing, and movement in your videos.

For camera speed effects, you can use the following terminology:
+ slow motion, slow-motion, slo-mo, slow-mo, slomo, slowmo
+ time-lapse, timelapse, time-lapse
+ hyperlapse
+ walklapse
+ spacelapse

For camera movement effects, you can use the following terminology:


| Camera Movement | Suggested Keywords | Definition | 
| --- |--- |--- |
| aerial shot |  Aerial shot. Aerial view. Drone shot. FPV drone shot. FPV aerial shot. First person view drone shot. First person view aerial shot.  | a shot taken from a drone or aircraft (FPV: first person view) | 
| arc shot |  Arc shot. 360 degree shot. 360 tracking shot. Orbit shot.  | camera moves in a circular path around a centrol point or an object. | 
| clockwise rotation |  Clockwise rotating shot. Camera rotates clockwise. Camera rolls clockwise. Camera rotates in clockwise direction. Camera rolls in clockwise direction.  | camera rotates in the clockwise direction. | 
| counterclockwise rotation |  Counterclockwise rotating shot. Anticlockwise rotating shot. Anti-clockwise rotating shot. Camera rotates counterclockwise. Camera rolls counterclockwise. Camera rotates anticlockwise. Camera rolls anticlockwise. Camera rotates anti-clockwise. Camera rolls anti-clockwise. Camera rotates in counterclockwise direction. Camera rolls in counterclockwise direction. Camera rotates in anticlockwise direction. Camera rolls in anticlockwise direction. Camera rotates in anti-clockwise direction. Camera rolls in anti-clockwise direction.  | camera rotates in the counterclockwise direction. | 
| dolly in |  Dolly in. Dolly in shot. Camera moves forward. Camera moving forward.  | moving the camera forward | 
| dolly out |  Dolly out. Dolly out shot. Camera moves backward. Camera moving backward.  | moving the camera backward | 
| pan left |  Pan left. Pan left shot. Camera pans left. Camera moves to the left.  | camera sweeps to the left from a fixed position | 
| pan right |  Pan right. Pan right shot. Camera pans right. Camera moves to the right.  | camera sweeps to the right from a fixed position | 
| whip pan |  Whip pan left. Whip pan right.  | fast pan shot | 
| pedestal down |  Pedestal down. Pedestal down shot. Ped-down. Ped-down shot. Camera moves down. Camera moving down.  | moving camera down | 
| pedestal up |  Pedestal up. Pedestal up shot. Ped-up. Ped-up shot. Camera moves up. Camera moving up.  | moving camera up | 
| static shot |  Static shot. Fixed shot.  | camera does not move. Note that object or subject in the video can still move. | 
| tilt down |  Tilt down. Tilt down shot. Pan down. Pan down shot. Camera tilts down. Camera tilting down. Camera pans down. Camera panning down. Camera moves down. Camera moving down.  | camera sweeps down from a fixed position | 
| tilt up |  Tilt up. Tilt up shot. Pan up. Pan up shot. Camera tilts up. Camera tilting up. Camera pans up. Camera panning up. Camera moves up. Camera moving up.  | camera sweeps up from a fixed position | 
| whip tilt |  Whip tilt up. Whip tilt down.  | fast tilt shot | 
| track left |  Track left. Truck left. Track left shot. Truck left shot. Camera tracking left. Camera trucking left. Camera tracks left. Camera trucks left. Camera moves to the left. Camera moving to the left.  | moving camera towards left | 
| track right |  Track right. Truck right. Track right shot. Truck right shot. Camera tracking right. Camera trucking right. Camera tracks right. Camera trucks right. Camera moves to the right. Camera moving to the right.  | moving camera towards right | 
| zoom in |  Zoom in. Zoom in shot. Camera zooms in. Camera zooming in. Camera moves forward.  | focal length of a camera lens is adjusted to give the illusion of moving closer to the subject. | 
| zoom out |  Zoom out. Zoom out shot. Camera zooms out. Camera zooming out. Camera moves backward.  | focal length of a camera lens is adjusted to give the illusion of moving further away from the subject. | 
| whip zoom |  Whip zoom in. Whip zoom out.  | fast zoom in or zoom out | 
| dolly zoom |  Dolly zoom. Dolly zoom shot. Dolly zoom effect. Zolly. Vertigo shot.  |  Use dolly and zoom at the same time to keep object size the same. It has two types:   dolly out \$1 zoom in   dolly in \$1 zoom out    | 
| following shot | Following shot. | follows the subject at a constant distance |