Topaz Labs

Topaz Labs

AI-powered video and image enhancement models

Topaz Labs provides AI video and image enhancement models available through Runware. Their Starlight models use diffusion AI technology to upscale, enhance, denoise, and sharpen video with full temporal consistency.

Models by Topaz Labs

Wonder 4 is Topaz Labs' all-purpose generative model for image enhancement and upscaling. It treats each region of an image separately, combining denoising, deblurring, compression artifact removal, face recovery, and upscaling in one pass with no settings to tune. It suits photo restoration, cleanup of degraded or compressed images, and enhancement at the original size or enlarged up to six times, with output up to 256 megapixels.

Wonder 3.5 is Topaz Labs' updated generative image enhancement and upscaling model for recovering detail and realism from both high-quality and degraded source images. It builds on Wonder 3 with finer detail generation, fewer repetitive patterns, improved handling of visual noise, and better precision on structured content such as tables, charts, and text-heavy graphics. It is well suited to photo restoration, compressed-image cleanup, creative enlargement, and enhancement workflows that need stronger texture recovery without drifting into overly artificial output.

Starlight Precise 2.5 is a diffusion-based video enhancement model from Topaz Labs that upscales, denoises, de-aliases, and sharpens video while maintaining full temporal consistency across frames. It delivers photorealistic detail with natural skin textures and faces, preserving the original look of the footage without artificial artifacts.

Proteus is Topaz Labs' general-purpose video enhancement model for upscaling and restoring a wide range of footage. It improves handling of noise, compression artifacts, faces, interlaced material, and scene transitions while maintaining stronger temporal consistency than earlier Proteus versions. Use it for broad video cleanup and enlargement workflows where the source does not call for a more specialized model.