Generative

Generative is tailored to the topaz/upscale/image/generative workflow for generative work in image production. Teams can place this named operation inside review, asset preparation, and publishing pipelines while keeping the original request attached to every result. Upscale Image Generative by Topaz Labs - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images effortlessly. Because topaz/upscale/image/generative is a separate catalog entry, evaluations should use this route’s own inputs, output expectations, and billing behavior. The endpoint is especially useful when a project has a defined transformation goal and needs a repeatable request contract instead of an ad-hoc desktop step. Those strengths describe this precise catalog entry rather than its siblings.

prompt controls text prompt to guide generative upscaling (max 1024 chars). Applies to Redefine model only; image controls url of the image to be upscaled; output format controls output format of the upscaled image; output format accepts jpeg, png; detail controls detail recovery level (0.0-1.0). Applies to Recovery V2 model only; subject detection controls subject detection mode for the image enhancement. Applies to Wonder 3, Recovery and Recovery V2 models; subject detection accepts All, Foreground, Background; upscale factor controls factor to upscale the image by (e.g. 2.0 doubles width and height). The mandatory portion is image, prompt. Generative exposes prompt, image, output_format, detail, subject_detection, upscale_factor, autoprompt as its documented request surface. For example, the route documentation includes “https://static.sandbase.ai/examples/topaz/upscale/image/generative/input_image_0.jpeg”. Applications can submit that exact shape asynchronously, retain the chosen arguments in job metadata, and collect the resulting media URL for review or publishing.

Highlights

• Generative image upscaling. Topaz Upscale Image Generative enlarges a supplied image and reconstructs plausible detail beyond simple pixel resampling.
• Texture synthesis. The model can add coherent surface information in regions that would otherwise become soft or blocky at larger dimensions.
• Source-guided composition. The input preserves the scene, subject placement, and broad visual identity while the enhancement concentrates on resolution and finish.
• High-resolution asset creation. It is useful when a chosen visual must be adapted for larger displays, print, or tighter crops.

Pricing

When to Use

Prompt Guide

Lead with the subject or transformation, then add the composition, environment, style, lighting, motion, voice, or fidelity details relevant to this route. Keep every parameter inside the documented schema; the example below uses only fields declared for topaz/upscale/image/generative.

{
  "prompt": "A polished editorial composition with clear subject, lighting, color, and camera direction.",
  "image": "https://static.sandbase.ai/examples/topaz/upscale/image/generative/input_image_0.jpeg",
  "output_format": "jpeg",
  "subject_detection": "All",
  "enhancement_strength": "low"
}

Technical Specs

Related Models

• topaz/colorize/video
• topaz/restore/image
• topaz/interpolate/video
• topaz/sdr-to-hdr/video