Hello 
Back with an early API release thread for the month of May!
We’ve had various great models in development, and we wanted to make these available to you all as soon as possible. This release features two new models to the API (one image model and one video model).
New Models
Two new models are now available in the API:
Face Recovery 3 — Generative diffusion model that excels at recovering rich, natural detail
Recover 3 is a generative image recovery model designed to reconstruct missing detail in low-resolution, damaged, or out-of-focus images, with a particular strength in restoring realistic facial features and natural textures. Now in its third generation, Recover 3 delivers significantly improved detail reconstruction, texture fidelity, and realism compared to earlier versions.
Recover intelligently rebuilds hair, skin, fabric, foliage, and other organic detail where original image information is limited or lost. It is especially effective for old photographs, heavily compressed images, and small or blurry faces, producing results that feel photographic rather than artificial.
A few of the key benefits of this model include:
-
Reconstructs missing facial features and fine textures with improved realism and stability over earlier Recover models.
-
Prioritizes believable skin, hair, and material textures while avoiding over-sharpened or plastic artifacts.
-
Realistic and Creative recovery options to balance fidelity versus detail generation, depending on source quality.
Hyperion 2 (SDR to HDR) — Advanced SDR to HDR conversion for professional finishing workflows
Hyperion 2 is a next-generation SDR to HDR conversion model designed to expand standard dynamic range footage into richer, higher dynamic range imagery with improved color handling, tonal separation, and detail preservation.
It automatically redistributes luminance and color information across highlights, midtones, and shadows while producing sharper, more detailed results, particularly in text, small faces, and fast motion. Hyperion 2 supports both PQ 12-bit ProRes workflows and 16-bit float EXR output for high-end HDR finishing and VFX pipelines.
A few of the key benefits of this model include:
-
Automatically converts SDR footage into HDR without requiring manual adjustment controls.
-
Produces brighter, more detailed HDR results with improved clarity in text, faces, and motion.
-
Supports 12-bit ProRes output in BT.2020 PQ color space and 16-bit float EXR output in ACES2065-1 color space for professional HDR mastering, grading, and compositing.
-
Ideal for converting 8-bit SDR and GenAI video sources into higher bit-depth formats for improved color grading and VFX finishing workflows
Note that before using this model, we highly recommend checking out the docs page for it, as we’ve added a section with details on supported codecs, important considerations, and more—check out those sections here!
We recommend referencing the linked model pages above to view full documentation that includes model descriptions, pricing, endpoints / parameters, and output examples.
As always, we’d love to hear your feedback, questions, and ideas! If you’d like to get involved, feel free to leave comments here in our community forum or in our Developer Discord!
Changelog
-
Launched two new models (one image, one video)
-
Recover 3
-
Hyperion 2 (SDR to HDR)
-
For any issues, reach out to support@topazlabs.com. Enterprise inquiries can be directed to enterprise@topazlabs.com.
Aiden Warnke
Product Manager
Enterprise & API
