Generating and Understanding Images, Audio, and Video on Bedrock

The situation

A media and operations team has landed two projects in the same sprint. Both briefs say “images”, so someone filed them under one ticket. The first is a marketing pipeline: from a product name and a short brief, produce on-brand hero images and a few seconds of promotional video, at volume, without a photoshoot. The second is a claims-intake pipeline. Customers upload PDFs, phone-camera photos of receipts, voicemails and short video clips. The business wants structured records out of all of it, so downstream systems can process a claim without anyone retyping it.

Both are “working with media on AWS”, and that is where the resemblance ends. One is generation, where the model produces the artefact. The other is understanding, where the model reads an artefact and returns structure. The tools barely overlap and the failure modes are opposite. The provenance question, can we prove which images our system made, lands on only one of them.

Solving both with “a model on Bedrock” is too coarse a plan. The first cut is which of the two jobs you are doing. Modality and output shape come after that.

What actually matters

Direction of travel decides everything downstream. Generation goes text to media: a prompt in, an image or a clip out. Understanding goes media to structure: an image, document, audio or video in, and fields, transcripts or a reasoned answer out. Name the direction first and you stop shortlisting services that solve the other problem well.

On the generation side, lifecycle status has stopped being trivia. Every entry ListFoundationModels returns carries a modelLifecycle field holding Active, Legacy or EOL. The Legacy state has concrete consequences. New customers cannot adopt a Legacy model at all, existing customers may lose access after fifteen days of inactivity, and no new Provisioned Throughput or fine-tuning job can be created against one. After the EOL date the model is removed from every Region and calls to it fail.

For models launched before 7 September 2026 the Legacy period runs at least six months, and after three of those months the model moves into public extended access at provider-set pricing, which is normally higher. Models launched since then carry an “EOL no sooner than” date on the model card plus a Legacy period of six months or forty-five days.

That policy shapes the generation half right now. Nothing in the catalogue turns a prompt into a still or a clip with an Active lifecycle. What survives is image editing, so the design question for a marketing pipeline is how much of the work can be done by transforming an asset that already exists.

The understanding side splits three ways by the shape you need out. Structured fields and tables from mixed media at volume, through one managed pipeline: Bedrock Data Automation. Deep control over a single modality, such as query-based extraction from an awkward layout or speaker-partitioned transcription: the purpose-built services. An answer rather than a schema: a multimodal foundation model reading the file in a prompt. The two mistakes are asking a multimodal model for free-form reasoning when you needed reliable fields, and standing up three single-purpose services where one pipeline covered the mix.

What we’ll filter on

1. Direction: generating media from a prompt, or reading media into structure or an answer?
2. Lifecycle: is the model Active, and is it callable from your Region at all?
3. Output shape (understanding only): strict fields and tables, single-modality precision, or free-form reasoning?
4. Breadth: one mixed stream of many media types, or one modality you want deep control over?
5. Provenance (generation only): do you need to prove later which images your system produced?
6. Operational fit: a managed pipeline with blueprints, a direct model call, or a parser wired into a Knowledge Base?

The landscape

Image generation. The catalogue lists two Amazon image generators and both are Legacy. Nova Canvas, amazon.nova-canvas-v1:0, went Legacy on 30 March 2026 and reaches EOL on 30 September 2026, in us-east-1, eu-west-1 and ap-northeast-1. Titan Image Generator G1 v2, amazon.titan-image-generator-v2:0, is already past its EOL date of 30 June 2026. Inference-parameter pages are still published for Stability’s Stable Image Core, stability.stable-image-core-v1:1, and Stable Image Ultra. Neither model appears in the models-at-a-glance catalogue or the regional availability tables, so read those pages as leftovers rather than a shopping list. Recognising the names in older material still helps; starting a pipeline on any of them does not.

Image editing. Thirteen Stability models are Active, and they are the working half of generation on Bedrock: inpaint, outpaint, erase object, search-and-replace, search-and-recolor, style guide, style transfer, control sketch, control structure, three upscalers, and remove background. Three of those make a new image rather than repairing one. Style guide follows a text prompt while matching a reference image’s style. Control sketch and control structure follow a prompt guided by a sketch or a depth map.

They run only through US geo cross-region inference. The model cards mark In-Region as unsupported in us-east-1, us-east-2 and us-west-2, and give a geo inference ID such as us.stability.stable-image-style-guide-v1:0 that routes across all three. Guardrails and abuse detection apply. Converse, response streaming, Agents, Flows and Knowledge Bases do not.

Video generation. Nova Reel is the only video generator in the catalogue, in two versions, amazon.nova-reel-v1:0 and amazon.nova-reel-v1:1, both Legacy with an EOL date of 30 September 2026. It runs as an asynchronous job through StartAsyncInvoke and writes the MP4 to an S3 bucket you name. The Luma Ray 2 reference page, luma.ray-v2:0, is likewise still published while the model is absent from the catalogue. After 30 September a new build has no video generator on Bedrock at all.

Bedrock Data Automation (BDA). A managed service that takes unstructured documents, images, audio and video and returns structured insights: fields and tables from documents, transcripts and summaries from audio and video, captions, detected text and moderation labels from images. Standard output is what you get by default. Custom output comes from blueprints, which describe the fields you want for a given document or media type, so a receipt and a claim form can yield different structures through the same pipeline. Confidence scores and visual grounding come back with the extraction.

Two shapes of call exist and they are not equivalent. InvokeDataAutomation, the synchronous one, only processes images. Everything else goes through InvokeDataAutomationAsync, polled with GetDataAutomationStatus, with results written to S3. Limits are worth knowing: async documents up to 500MB and 3,000 pages with the splitter enabled, images up to 5MB, audio and video up to 240 minutes each, and 40 blueprints per project against 1,000 per account. BDA also plugs into a Bedrock Knowledge Base as a parser, converting uploads to text (transcripts and scene summaries) before the usual chunking runs.

Purpose-built AI services. Amazon Textract reads documents: text detection, forms and tables through AnalyzeDocument, targeted extraction through Queries, invoices and receipts through AnalyzeExpense, identity documents through AnalyzeID. Amazon Transcribe turns speech into text in batch or streaming, partitions speakers, handles multi-channel audio and takes custom vocabulary. Amazon Rekognition analyses images and video for objects, scenes, text, faces and unsafe content. Each is deep in one lane, tunable, and long established.

Multimodal foundation models. Nova 2 Lite, Nova Lite, Nova Pro and Claude on Bedrock accept an image or a document alongside the text prompt and answer questions about it: what is wrong with this diagram, does this receipt match this policy, what is the person in this photo doing. No blueprint, no fixed schema. That suits a fuzzy or one-off question rather than a repeatable extraction job.

Evaluation

Nova Canvas, Nova Reel and Titan Image Generator are missing from the table below on purpose. All three are Legacy, which means a new project cannot adopt them, and two of them stop working entirely on 30 September 2026.

Side by side

The solution

The marketing pipeline is a generation job, and Bedrock covers only part of it. For the stills, the Active path is Stability’s style guide model: give it the brand’s reference image and a text prompt per product, and it follows the look across a set. Control sketch and control structure do the same trick from a layout rather than a style. Remove background drops the result onto the clean canvas the brand guidelines require, inpaint fixes a detail, and an upscaler takes the chosen frame to campaign resolution. Every one of those is a separate model id, not a mode of one generator, so the pipeline is a short chain of calls rather than a single invoke.

Call these through the geo inference ID. In-Region invocation is not offered for the Stability editing family; the ids are prefixed us. and route across us-east-1, us-east-2 and us-west-2. A pipeline that hardcodes the bare stability. id fails on a model that is otherwise available to the account.

The clip has no answer on Bedrock past September. Nova Reel still runs until 30 September 2026 for an account already using it, and after that date there is no video generator in the catalogue. A team committing to promotional video needs a decision now: a provider outside Bedrock, or a scope that stops at stills. Design the call site so the model is swappable, because the asynchronous job shape (start, poll, collect from S3) is the part that survives whichever model replaces it.

Provenance has to be recorded, not read back. The invisible watermark was an Amazon feature: Nova Canvas and Titan Image Generator G1 embedded it, and Bedrock’s watermark detection, a preview feature in us-east-1 and us-west-2, reads it back. Both models are leaving, and nothing in the Stability documentation describes anything comparable. If the brand needs to answer “did our system make this?” a year from now, the pipeline answers it from its own records. Log the model id, the prompt, the reference image, the seed, the Region and a hash of the bytes as each asset is produced, and keep that ledger with the asset library. File metadata helps until the first crop-and-recompress strips it, so the ledger and the hash are the durable part.

The claims-intake pipeline is an understanding job, and the answer is BDA. The input is mixed: PDFs, photos, voicemails and clips arriving together, all needing to become records. That is the case BDA is built for, one managed API across four modalities instead of a routing layer that sniffs each upload and dispatches it. Blueprints define what “a claim form” and “a receipt” should yield, so downstream systems see the same fields every time. Wiring BDA in as the Knowledge Base parser makes the same corpus retrievable, so a support assistant can answer questions grounded in the uploads without a second ingestion path.

When to walk away from BDA toward a purpose-built service. If the stream is actually one modality with an exacting requirement, the answer flips. Scanned forms with awkward layouts needing the strongest OCR, query-based extraction and signature detection are a Textract job. Audio needing speaker partitioning, custom vocabulary and per-channel transcription is a Transcribe job. Moderation and object detection across a video library is a Rekognition job. BDA’s advantage is breadth; the purpose-built services go deeper in one lane. Standing up all three to reconstruct what BDA does in one call wastes the breadth, and forcing a precision task through a generalist pipeline wastes the depth.

When the answer is neither. If the requirement is “read this and tell me something” rather than “extract these fields every time”, the tool is a multimodal model reasoning over the file in the prompt. Does this receipt match the policy the customer quoted? Is the damage in this photo consistent with the described incident? Nova Pro or Claude reading the image answers that in language. Pushing the same question into BDA’s structured output, or into Rekognition’s label set, gets a shape that does not fit the question.

Worked example

One web form feeds both pipelines, and two items arrive in the same minute. Marketing submits a brief: matte black insulated flask, studio lighting, plain background, in the house look. The claims team’s customer uploads a phone photo of a damaged flask, a PDF claim form and a ten-second voicemail.

The brief goes to generation. The brand’s reference image and the product prompt go to style guide, and the result goes through remove background and an upscaler. Note the model id.

brand_style = base64.b64encode(open("brand-reference.png", "rb").read()).decode()

still = bedrock_runtime.invoke_model(              # any of us-east-1/2, us-west-2
    modelId="us.stability.stable-image-style-guide-v1:0",   # geo id, not stability.*
    body=json.dumps({
        "image": brand_style,
        "prompt": "matte black insulated flask, studio lighting, plain background",
    }),
)

png = base64.b64decode(json.loads(still["body"].read())["images"][0])

The us. prefix is not optional. These models list In-Region inference as unsupported, so the bare id fails even though the account has access and the Region is right. The provenance record is written here, at the moment the bytes exist, because nothing in the output carries one.

The claims upload goes to understanding, and mixed media means BDA. The synchronous API handles images only, so a PDF, a photo and a voicemail arriving together go through the asynchronous one.

job = bda_runtime.invoke_data_automation_async(    # bedrock-data-automation-runtime
    inputConfiguration={"s3Uri": "s3://claims-intake/2026/08/claim-8812/"},
    outputConfiguration={"s3Uri": "s3://claims-structured/claim-8812/"},
    dataAutomationConfiguration={
        "dataAutomationProjectArn": CLAIMS_PROJECT_ARN,
        "stage": "LIVE",
    },
    dataAutomationProfileArn=PROFILE_ARN,
    blueprints=[{"blueprintArn": CLAIM_FORM_BLUEPRINT, "stage": "LIVE"}],
)

status = bda_runtime.get_data_automation_status(invocationArn=job["invocationArn"])
if status["status"] == "Success":
    print(status["outputConfiguration"]["s3Uri"])

The blueprint pulls claimant, policy number and itemised loss from the form. The voicemail comes back as a transcript and a summary, the photo as a caption with detected text and moderation labels. Results land in S3 rather than in the response, so a pipeline of any size makes this a step in a state machine instead of a thread in a request handler.

Because the same project parses the Knowledge Base data source, the upload is retrievable as well as structured, and the assistant can answer “what did the customer say happened?” from the transcript. When a supervisor asks whether the damage in the photo matches the described incident, that is not extraction at all. The photo and the transcript go to a multimodal model, which returns a judgement in language. One intake form, three tools, chosen by direction first and output shape second.

What’s worth remembering

1. The first cut is which job, not which model: generation writes media from a prompt, understanding reads media into structure or an answer.
2. Legacy on Bedrock blocks new adoption outright, cuts existing users off after fifteen days of inactivity, and blocks new Provisioned Throughput and fine-tuning, so lifecycle status is a design input rather than a footnote.
3. No model in the catalogue turns a prompt into a still or a clip with an Active lifecycle; Nova Canvas and Nova Reel reach EOL on 30 September 2026 and Titan Image Generator passed its own date in June.
4. The thirteen Stability editing models are Active, and three of them (style guide, control sketch, control structure) make a new image from a prompt plus a reference; all thirteen need the us. geo inference ID.
5. Bedrock Data Automation is one managed pipeline across documents, images, audio and video, configured with blueprints, synchronous for images only and asynchronous for everything else, and usable as a Knowledge Base parser.
6. Reach for Textract, Transcribe or Rekognition when one modality needs depth, and for a multimodal model when you want an answer rather than a schema.