|
At re:Invent 2024, we introduced Amazon Nova fashions, a brand new era of foundation fashions (FMs), together with Amazon Nova Reel, a video era mannequin that creates quick movies from textual content descriptions and elective reference photographs (collectively, the “prompt”).
Today, we introduce Amazon Nova Reel 1.1, which supplies high quality and latency enhancements in 6-second single-shot video era, in comparison with Amazon Nova Reel 1.0. This replace enables you to generate multi-shot movies as much as 2-minutes in size with constant type throughout photographs. You can both present a single immediate for as much as a 2-minute video composed of 6-second photographs, or design every shot individually with customized prompts. This offers you new methods to create video content material via Amazon Bedrock.
Amazon Nova Reel enhances artistic productiveness, whereas serving to to cut back the time and price of video manufacturing utilizing generative AI. You can use Amazon Nova Reel to create compelling movies in your advertising campaigns, product designs, and social media content material with elevated effectivity and inventive management. For instance, in promoting campaigns, you may produce high-quality video commercials with constant visuals and timing utilizing pure language.
To get began with Amazon Nova Reel 1.1
If you’re new to utilizing Amazon Nova Reel fashions, go to the Amazon Bedrock console, select Model entry within the navigation panel and request entry to the Amazon Nova Reel mannequin. When you get entry to Amazon Nova Reel, it applies each to 1.0 and 1.1.
After gaining entry, you may attempt Amazon Nova Reel 1.1 straight from the Amazon Bedrock console, AWS SDK, or AWS Command Line Interface (AWS CLI).
To take a look at the Amazon Nova Reel 1.1 mannequin within the console, select Image/Video underneath Playgrounds within the left menu pane. Then select Nova Reel 1.1 because the mannequin and enter your immediate to generate video.
Amazon Nova Reel 1.1 presents two modes:
- Multishot Automated – In this mode, Amazon Nova Reel 1.1 accepts a single immediate of as much as 4,000 characters and produces a multi-shot video that displays that immediate. This mode doesn’t settle for an enter picture.
- Multishot Manual – For those that want extra direct management over a video’s shot composition, with handbook mode (additionally known as storyboard mode), you may specify a singular immediate for every particular person shot. This mode does settle for an elective beginning picture for every shot. Images should have a decision of 1280×720. You can present photographs in base64 format or from an Amazon Simple Storage Service (Amazon S3) location.
For this demo, I take advantage of the AWS SDK for Python (Boto3) to invoke the mannequin utilizing the Amazon Bedrock API and StartAsyncInvoke operation to start out an asynchronous invocation and generate the video. I used GetAsyncInvoke to test on the progress of a video era job.
This Python script creates a 120-second video utilizing MULTI_SHOT_AUTOMATED mode as TaskType parameter from this textual content immediate, created by Nitin Eusebius.
import random import time import boto3 AWS_REGION = "us-east-1" MODEL_ID = "amazon.nova-reel-v1:1" SLEEP_SECONDS = 15 # Interval at which to test video gen progress S3_DESTINATION_BUCKET = "s3://" video_prompt_automated = "Norwegian fjord with nonetheless water reflecting mountains in good symmetry. Uninhabited wilderness of Giant sequoia forest with daylight filtering between huge trunks. Sahara desert sand dunes with good ripple patterns. Alpine lake with crystal clear water and mountain reflection. Ancient redwood tree with detailed bark texture. Arctic ice cave with blue ice partitions and ceiling. Bioluminescent plankton on seaside shore at evening. Bolivian salt flats with good sky reflection. Bamboo forest with tall stalks in filtered mild. Cherry blossom grove towards blue sky. Lavender subject with purple rows to horizon. Autumn forest with crimson and gold leaves. Tropical coral reef with fish and colourful coral. Antelope Canyon with mild beams via slim passages. Banff lake with turquoise water and mountain backdrop. Joshua Tree desert at sundown with silhouetted timber. Iceland moss- coated lava subject. Amazon lily pads with good symmetry. Hawaiian volcanic panorama with lava rock. New Zealand glowworm cave with blue ceiling lights. 8K nature pictures, skilled panorama lighting, no motion transitions, good publicity for every atmosphere, pure shade grading" bedrock_runtime = boto3.shopper("bedrock-runtime", region_name=AWS_REGION) model_input = { "taskType": "MULTI_SHOT_AUTOMATED", "multiShotAutomatedParams": {"textual content": video_prompt_automated}, "videoGenerationConfig": { "durationSeconds": 120, # Must be a a number of of 6 in vary [12, 120] "fps": 24, "dimension": "1280x720", "seed": random.randint(0, 2147483648), }, } invocation = bedrock_runtime.start_async_invoke( modelId=MODEL_ID, mannequinInput=model_input, outputDataConfig={"s3OutputDataConfig": {"s3Uri": S3_DESTINATION_BUCKET}}, ) invocation_arn = invocation["invocationArn"] job_id = invocation_arn.cut up("/")[-1] s3_location = f"{S3_DESTINATION_BUCKET}/{job_id}" print(f"nMonitoring job folder: {s3_location}") whereas True: response = bedrock_runtime.get_async_invoke(invocationArn=invocation_arn) standing = response["status"] print(f"Status: {standing}") if standing != "InProgress": break time.sleep(SLEEP_SECONDS) if standing == "Completed": print(f"nVideo is prepared at {s3_location}/output.mp4") else: print(f"nVideo era standing: {standing}")
After the primary invocation, the script periodically checks the standing till the creation of the video has been accomplished. I move a random seed to get a distinct consequence every time the code runs.
I run the script:
Status: InProgress
. . .
Status: Completed
Video is prepared at s3:////output.mp4
After a couple of minutes, the script is accomplished and prints the output Amazon S3 location. I obtain the output video utilizing the AWS CLI:
aws s3 cp s3:////output.mp4 output_automated.mp4 This is the video that this immediate generated:
In the case of MULTI_SHOT_MANUAL mode as TaskType parameter, with a immediate for multiples photographs and an outline for every shot, it’s not needed so as to add the variable durationSeconds.
Using the immediate for multiples photographs, created by Sanju Sunny.
I run Python script:
import random import time import boto3 def image_to_base64(image_path: str): """ Helper operate which converts a picture file to a base64 encoded string. """ import base64 with open(image_path, "rb") as image_file: encoded_string = base64.b64encode(image_file.learn()) return encoded_string.decode("utf-8") AWS_REGION = "us-east-1" MODEL_ID = "amazon.nova-reel-v1:1" SLEEP_SECONDS = 15 # Interval at which to test video gen progress S3_DESTINATION_BUCKET = "s3://" video_shot_prompts = [ # Example of using an S3 image in a shot. { "text": "Epic aerial rise revealing the landscape, dramatic documentary style with dark atmospheric mood", "image": { "format": "png", "source": { "s3Location": {"uri": "s3:// /images/arctic_1.png"} }, }, }, # Example of using a locally saved image in a shot { "text": "Sweeping drone shot across surface, cracks forming in ice, morning sunlight casting long shadows, documentary style", "image": { "format": "png", "source": {"bytes": image_to_base64("arctic_2.png")}, }, }, { "text": "Epic aerial shot slowly soaring forward over the glacier's surface, revealing vast ice formations, cinematic drone perspective", "image": { "format": "png", "source": {"bytes": image_to_base64("arctic_3.png")}, }, }, { "text": "Aerial shot slowly descending from high above, revealing the lone penguin's journey through the stark ice landscape, artic smoke washes over the land, nature documentary styled", "image": { "format": "png", "source": {"bytes": image_to_base64("arctic_4.png")}, }, }, { "text": "Colossal wide shot of half the glacier face catastrophically collapsing, enormous wall of ice breaking away and crashing into the ocean. Slow motion, camera dramatically pulling back to reveal the massive scale. Monumental waves erupting from impact.", "image": { "format": "png", "source": {"bytes": image_to_base64("arctic_5.png")}, }, }, { "text": "Slow motion tracking shot moving parallel to the penguin, with snow and mist swirling dramatically in the foreground and background", "image": { "format": "png", "source": {"bytes": image_to_base64("arctic_6.png")}, }, }, { "text": "High-altitude drone descent over pristine glacier, capturing violent fracture chasing the camera, crystalline patterns shattering in slow motion across mirror-like ice, camera smoothly aligning with surface.", "image": { "format": "png", "source": {"bytes": image_to_base64("arctic_7.png")}, }, }, { "text": "Epic aerial drone shot slowly pulling back and rising higher, revealing the vast endless ocean surrounding the solitary penguin on the ice float, cinematic reveal", "image": { "format": "png", "source": {"bytes": image_to_base64("arctic_8.png")}, }, }, ] bedrock_runtime = boto3.shopper("bedrock-runtime", region_name=AWS_REGION) model_input = { "taskType": "MULTI_SHOT_MANUAL", "multiShotManualParams": {"photographs": video_shot_prompts}, "videoGenerationConfig": { "fps": 24, "dimension": "1280x720", "seed": random.randint(0, 2147483648), }, } invocation = bedrock_runtime.start_async_invoke( modelId=MODEL_ID, mannequinInput=model_input, outputDataConfig={"s3OutputDataConfig": {"s3Uri": S3_DESTINATION_BUCKET}}, ) invocation_arn = invocation["invocationArn"] job_id = invocation_arn.cut up("/")[-1] s3_location = f"{S3_DESTINATION_BUCKET}/{job_id}" print(f"nMonitoring job folder: {s3_location}") whereas True: response = bedrock_runtime.get_async_invoke(invocationArn=invocation_arn) standing = response["status"] print(f"Status: {standing}") if standing != "InProgress": break time.sleep(SLEEP_SECONDS) if standing == "Completed": print(f"nVideo is prepared at {s3_location}/output.mp4") else: print(f"nVideo era standing: {standing}")
As within the earlier demo, after a couple of minutes, I obtain the output utilizing the AWS CLI:aws s3 cp s3://
This is the video that this immediate generated:
More artistic examples
When you employ Amazon Nova Reel 1.1, you will uncover a world of artistic potentialities. Here are some pattern prompts that will help you start:
Color Burst, created by Nitin Eusebius
immediate = "Explosion of coloured powder towards black background. Start with slow-motion closeup of single purple powder burst. Dolly out revealing a number of powder clouds in vibrant hues colliding mid-air. Track throughout spectrum of colours mixing: magenta, yellow, cyan, orange. Zoom in on particles illuminated by sunbeams. Arc shot capturing full shade subject. 4K, competition celebration, high-contrast lighting"
Shape Shifting, created by Sanju Sunny
All instance movies have music added manually earlier than importing, by the AWS Video crew.
Things to know
Creative management – You can use this enhanced management for life-style and ambient background movies in promoting, advertising, media, and leisure initiatives. Customize particular components akin to digicam movement and shot content material, or animate current photographs.
Modes issues – In automated mode, you may write prompts as much as 4,000 characters. For handbook mode, every shot accepts prompts as much as 512 characters, and you’ll embody as much as 20 photographs in a single video. Consider planning your photographs prematurely, much like creating a conventional storyboard. Input photographs should match the 1280×720 decision requirement. The service robotically delivers your accomplished movies to your specified S3 bucket.
Pricing and availability – Amazon Nova Reel 1.1 is out there in Amazon Bedrock within the US East (N. Virginia) AWS Region. You can entry the mannequin via the Amazon Bedrock console, AWS SDK, or AWS CLI. As with all Amazon Bedrock companies, pricing follows a pay-as-you-go mannequin primarily based in your utilization. For extra data, seek advice from Amazon Bedrock pricing.
Ready to start out creating with Amazon Nova Reel? Visit the Amazon Nova Reel AWS AI Service Cards to study extra and dive into the Generating movies with Amazon Nova. Explore Python code examples within the Amazon Nova mannequin cookbook repository, improve your outcomes utilizing the Amazon Nova Reel prompting greatest practices, and uncover video examples within the Amazon Nova Reel gallery—full with the prompts and reference photographs that introduced them to life.
The potentialities are infinite, and we stay up for seeing what you create! Join our rising group of builders at community.aws, the place you may create your BuilderID, share your video era initiatives, and join with fellow innovators.
— Eli
How is the News Blog doing? Take this 1 minute survey!
(This survey is hosted by an exterior firm. AWS handles your data as described within the AWS Privacy Notice. AWS will personal the information gathered through this survey and won’t share the knowledge collected with survey respondents.)