Amazon Nova Reel 1.1
Amazon Nova Reel generates video from text prompts or from text plus an image, and is available only through Amazon Bedrock.
- Up to
- 120 seconds
- Resolution
- 1280x720 at 24fps
- Aspect ratios
- 16:9
- Weights
- Not released
- API
- Yes
- Commercial use
- Not established
AWS documents output at 1280x720 and 24 frames per second, produced in six-second increments up to a total of two minutes; generating anything longer than six seconds requires model ID amazon.nova-reel-v1:1. It also supports a storyboard mode for composing multi-shot sequences.
The research notes for this model record other terms but do not state a commercial-use position, and no licence page was retrieved, so it is not established here. Check the vendor's own terms.
- The terms restrict what you may generate. Governed by the AWS Service Terms and Amazon Bedrock's acceptable-use policy; not reviewed in this pass
Specification
- What it takes in
- text, image
- What it makes
- video
- Maximum duration
- 120 seconds
- Maximum resolution
- 1280x720 at 24fps
- Aspect ratios
- 16:9
- Controls
- image-to-video, keyframes
- Weights
- Not released
- API
- Yes
- Pricing
- Billed through Amazon Bedrock; AWS Bedrock's per-second Nova Reel rate was not retrieved during this pass, so recorded as unverified.
- Released or updated
- Nova Reel 1.1 (amazon.nova-reel-v1:1); AWS announced 1.1 in April 2025 per its What's New feed, docs current as of 2026-08-14
Strengths
- Longest documented output of any model in this set: up to two minutes
- Storyboard mode for multi-shot narrative structure
- Runs inside existing AWS accounts with IAM, VPC and Bedrock guardrails
- 24fps output is documented explicitly, which most vendors omit
Weaknesses
- 720p only; no 1080p or 4K
- Composed of six-second increments rather than a single continuous take
- 16:9 is the only documented dimension
- No native audio
- Available only via Bedrock, so no direct consumer product
Best for
- Enterprises already on AWS that need long-form, policy-controlled video generation rather than maximum fidelity.
See it from the vendor
Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.
Nearby in the directory
Adobe Firefly Video Model
The Adobe Firefly Video Model generates video from a text prompt, optionally guided by an image used as the first or final frame. Adobe's Firefly Serv
Video generation
Allegro
A small text-to-video model comprising a 2.8B VideoDiT and a 175M VideoVAE, released under Apache-2.0 in October 2024. It generates 88-frame clips at
Video generation
ByteDance Seedance 2.0
Seedance 2.0 is ByteDance Seed's unified multimodal audio-video model: a single generation pass accepts text plus mixed references (up to 9 images, 3
Video generation