Which parameters does the Topaz upscale API expose (model, upscale_factor, target_fps, recover_detail), and when should I not upscale an AI video at all?
Problem. Choosing whether and how to upscale generated footage. Conditions. Topaz upscaling via fal's API (hosted). Method. Parameters: video_url; model (Proteus default; Artemis for denoise+sharpen; Nyx for dedicated denoising; Gaia HQ/CG for rendered content; Gaia 2 for animation and motion graphics at 2x; Starlight variants for generative diffusion-based upscaling); upscale_factor 1 to 4 (default 2); target_fps 16 to 60 which turns on frame interpolation; compression, noise, halo and grain levels 0-1; recover_detail 0-1 where higher preserves more original detail; H264_output (default H265). Decision rules (inference, combining with C3-B582-11, -12): (1) upscale last, on the final graded cut; (2) do not upscale 1080p clean AIGC unless a delivery spec needs it, since generative upscalers can over-sharpen already clean input (SeedVR2 limitation); (3) for faces and text that must match references, raise recover_detail, avoid generative 'Starlight' style modes, and compare crops at 1...
Structured fields
{
"citations": [
{
"url": "https://fal.ai/docs/model-api-reference/video-generation-api/topaz-upscale",
"note": "Input Schema: model; Input Schema: upscale_factor; Input Schema: target_fps; Input Schema: recover_detail; Input Schema: H264_output; Limitations; decision rules"
},
{
"url": "https://raw.githubusercontent.com/ByteDance-Seed/SeedVR/main/readme.md",
"note": "Input Schema: model; Input Schema: upscale_factor; Input Schema: target_fps; Input Schema: recover_detail; Input Schema: H264_output; Limitations; decision rules"
}
]
}Evidence claims
- [sourced_fact] Problem. Choosing whether and how to upscale generated footage. Conditions. Topaz upscaling via fal's API (hosted). Method. Parameters: video_url; model (Proteus default; Artemis for denoise+sharpen; Nyx for dedicated denoising; Gaia HQ/CG for rendered content; Gaia 2 for animation and motion graphics at 2x; Starlight variants for generative diffusion-based upscaling); upscale_factor 1 to 4 (default 2); target_fps 16 to 60 which turns on frame interpolation; compression, noise, halo and grain levels 0-1; recover_detail 0-1 where higher preserves more original detail; H264_output (default H265). Decision rules (inference, combining with C3-B582-11, -12): (1) upscale last, on the final graded cut; (2) do not upscale 1080p clean AIGC unless a delivery spec needs it, since generative upscalers can over-sharpen already clean input (SeedVR2 limitation); (3) for faces and text that must match references, raise recover_detail, avoid generative 'Starlight' style modes, and compare crops at 100%; (4) frame interpolation via target_fps can add motion artefacts on fast action (see C3-B079-G30-02); (5) keep an unprocessed master. Failure modes. Hallucinated texture on faces or lettering, flicker in invented detail (inference). Limitations. The fal page lists parameters but no quality statements; pricing deliberately not recorded; the model descriptions are vendor wording. Version/date. fal reference fetched 2026-10-23. · locator: Input Schema: model; Input Schema: upscale_factor; Input Schema: target_fps; Input Schema: recover_detail; Input Schema: H264_output; Limitations; decision rules source
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| documentation | unknown | permitted | permitted | unknown | unknown | Applies to this original summary only, not to the cited sources. |