Upscale an Image
Submit an image and retrieve the enhanced output.
/oo Topaz: Use Topaz to upscale [image URL] to 2048 pixels wide and return the download link.
Submit image URLs or videos in S3 storage for enhancement and retrieve processed results.
20,000 free app calls every month(paid services billed separately)
Copy a prompt into your agent with the oo Skill installed. Add your page links and source notes before running it.
Submit an image and retrieve the enhanced output.
/oo Topaz: Use Topaz to upscale [image URL] to 2048 pixels wide and return the download link.
Process a video from S3 and track its progress.
/oo Topaz: Enhance [S3 presigned video URL] with Topaz using [model] and [output resolution], preserving audio.
Set up oo CLI and the oo Skill in your agent.
Install OOMOL →Connect a Topaz API key.
Connect Topaz→Use /oo with the pages to read, the changes to make, and where to save the result.
Connection Guide →Choose Your Agent
Access precision and generative image enhancement, sharpening, denoising, restoration, lighting, matting and transparency upscaling. Estimate processing costs, manage image and video jobs, retrieve downloads, inspect video metrics, and query API credit usage.
Process images, estimate costs, inspect history, download originals and results, and cancel or remove job records.
Create and process video jobs, inspect models, estimates, metrics and history, manage upload completion, cancel requests and delete files.
Check current credit balances and historical API consumption.
List image jobs. Pagination defaults to true; non-paginated mode returns jobs up to seven days old. Follow next_cursor while has_next_page is true.
topaz.list_image_jobsDelete one image job status record. This is separate from cancelling a running job.
topaz.delete_image_job_statusDelete all image processing status records, clearing the account's job history.
topaz.delete_all_image_job_statusesGet temporary download and HEAD links for the original input image.
topaz.get_image_input_downloadEstimate standard image processing credits and duration without submitting a job.
topaz.estimate_imageEstimate generative image processing credits and duration without submitting a job.
topaz.estimate_generative_imageEstimate multiple image jobs in one request. Each result may succeed or contain its own error.
topaz.estimate_images_bulkGet video service availability and the authoritative list of currently supported model codes.
topaz.get_video_system_statusCreate a standard video request and receive cost estimates. No credits are charged and processing does not start until accept_video_request. Prefer submit_video_enhancement for automatic external-source processing.
topaz.create_video_requestAccept estimated video costs and reserve credits. External sources start processing automatically. Otherwise PUT source bytes to the returned upload URLs and call complete_video_upload; repeated calls return the same URLs.
topaz.accept_video_requestComplete an externally performed video upload and start processing. For one upload URL send [{partNum:1,eTag:unused}]; multipart uploads require the actual ordered part numbers and ETags returned by storage.
topaz.complete_video_uploadPreview credits committed and refunded if a video request were cancelled now, without cancelling it.
topaz.estimate_video_cancellationPermanently delete the source and enhanced video files stored by Topaz for a request.
topaz.delete_video_filesGet the full video request record, including unaccepted requests, corrected source metrics, credit transactions and signed downloads.
topaz.get_video_requestGet video processing metrics. Requests without chunked processing may return only a message indicating metrics are unavailable.
topaz.get_video_metricsList accepted video requests newest first. Follow nextCursor until null, even when a page has fewer than 50 entries. Unaccepted requests are omitted.
topaz.list_video_requestsGet historical API credit consumption by time bucket. Explicit date ranges override period. period=1d covers 48 hours; sparse buckets do not imply missing requests.
topaz.get_credit_usageSubmit a precision image upscale job to Topaz. Returns a job ID for polling.
topaz.submit_image_enhancementSubmit a generative image enhancement job to Topaz. Returns a job ID for polling.
topaz.submit_generative_image_enhancementSubmit image sharpening to restore sharpness and reduce blur.
topaz.submit_image_sharpeningSubmit generative image sharpening for severe blur recovery.
topaz.submit_generative_image_sharpeningSubmit image denoising to remove noise while retaining detail.
topaz.submit_image_denoisingSubmit generative photo restoration to remove dust and scratches.
topaz.submit_image_restorationSubmit image lighting, white balance or colorization processing.
topaz.submit_image_lightingSubmit image object matting and return a PNG with transparency.
topaz.submit_image_mattingSubmit transparency-preserving image upscaling using the Tool API.
topaz.submit_image_toolGet an image job status and progress. After completion use get_image_download to retrieve the result URL.
topaz.get_image_jobGet a completed image's temporary download and HEAD URLs, valid for one hour.
topaz.get_image_downloadCancel a pending image job. Completed or non-cancellable jobs return a conflict.
topaz.cancel_image_jobSubmit video enhancement or frame interpolation through Express using S3 external storage. Topaz fetches the source and starts processing immediately. Preserve audio explicitly with audioTransfer and audioCodec.
topaz.submit_video_enhancementGet video processing status, progress, estimates and the completed result download link. Download links are reused and expire after their original lifetime.
topaz.get_video_jobCancel a video job. Topaz may refund credits in full before processing or partially during processing.
topaz.cancel_video_jobGet available, reserved and total Topaz API credits.
topaz.get_credit_balanceNo matching tools.
Processing is asynchronous. Submit a job, query its status and retrieve the completed result.
Yes. create_video_request returns estimates without starting processing. accept_video_request accepts the costs. Express instead starts external-source processing immediately.