Starlight HQ
Maximum quality generative enhancement for modern high-resolution video
Model Overview
Starlight HQ is a high quality enhancement model designed for modern, high resolution video sources. It delivers a strong balance of detail and sharpness while preserving the visual intent of the original footage.
Unlike restoration focused models such as Starlight Mini, HQ is optimized for clean progressive video and larger source resolutions. It supports inputs from 480p through 4K and can render native 4K outputs, making it well suited for modern digital camera footage and high resolution finishing.
Starlight HQ can run locally in Topaz Video or in the cloud via API. For local processing, the model uses a larger architecture that prioritizes visual fidelity over speed and requires an NVIDIA GPU with at least 10GB of VRAM, with 12GB or more recommended.
Key Capabilities
High fidelity diffusion enhancement for modern digital camera sources
Supports larger inputs up to 4K with native 4K output
Ideal for high resolution workflows where maximum visual quality is the priority
Pricing
26.0417
11.9179
Endpoint
Parameters
model
Model name:
inputFrameCount
Input video number of frames.
inputFrameRate
Input video frame rate in frames per second.
inputHeight
Input video height in pixels.
inputWidth
Input video width in pixels.
outputHeight
Output video height in pixels.
outputWidth
Output video width in pixels.
videoBitDepth
Output video bit depth.
videoCodec
Output video codec.
Possible values: , ,
videoProfile
Output video profile.
Possible values: , ,
startIdx
First frame of the source video to process. Pair with to only render a segment of the video.
endIdx
Last frame of the source to process. Default of effectively renders the entire clip.
ffmpegEncoding
Override for the output encoder settings passed to FFmpeg (codec, quality/bitrate, pixel format).
ffmpegReprocFilters
FFmpeg filter chain applied to the source pre-processing (e.g. crop, deinterlace, or color conversion).
keepOriginal
Preserves the source's non-video streams and metadata (audio, subtitles, timecode) in the output.
upscalingFactor
Output resolution multiplier relative to the source. keeps output resolution the same.
Range: to
watermark
Whether to watermark the output.
Examples
Last updated