Hi rcoquet.
Here’s a brief introduction to the three different High Fidelity Models from the Topaz Documentation Pages
High Fidelity
**
High Fidelity (v1):** Best for enhancing already high-quality images while preserving natural detail. Ideal for DSLR and modern smartphone photos where you want a clean upscale without altering the original look.
High Fidelity (v2): Best for high-quality images where you want to retain original character such as grain or noise. Produces a slightly more stylized result while still preserving detail, useful for artistic or aesthetic intent.
High Fidelity (v3): New, released in Topaz Photo v1.5.0. Best for high-resolution, detail-rich images where maximum realism is needed. Enhances fine textures, reduces repetitive artifacts, and produces sharper, more natural results at larger upscale sizes while staying true to the original image.
Here’s a bit more information about High Fidelity v3 from the Topaz Release Pages
High Fidelity v3 — Better Detail, Fewer Artifacts
High Fidelity is designed for images that are already in good shape. Where other models focus on recovery, High Fidelity’s job is to enhance what’s already there: sharper detail, cleaner textures, and upscaled output that holds up at full resolution. v3 raises the bar on all of these, and fixes the cases where v2 fell short.
The core change in v3 is a two-part architecture. Before upscaling begins, an analysis model reads the image, both as a whole and at the block level, to build a detailed understanding of its content. The upscaling model then uses that context to produce output that stays true to the original while generating realistic detail even at larger upscale values. Earlier models would struggle here, as small structures get magnified significantly and realistic detail becomes much harder to maintain.
This approach also meaningfully reduces AI artifacts. Two areas we’re especially happy with: natural scenes and skin. Leaves, grass, and similar patterns used to come out repetitive and visibly generated. v3 produces realistic variation. Skin textures, which previously came out either too smooth or too harsh, now retain their natural softness.
Beyond artifact reduction, v3 is better at preserving and enhancing textures that are already present in the image. Rather than softening fine detail during upscaling, it sharpens it further, producing a crispness that previous High Fidelity models couldn’t match.
High Fidelity v3 is best suited for images that are already high resolution and clearly detailed. Raw files and images above 6MP are ideal candidates. If the source image has strong existing detail, v3 will enhance it further rather than approximate it. For lower resolution or lower quality images, Wonder 3 is the better starting point.
We want to hear how it performs on your images, especially on subjects where v2 produced repetitive textures or visible artifacts. Drop your results and feedback in this thread.
Produces a slightly more stylized result while still preserving detail, useful for artistic or aesthetic intent.
The description for High Fidelity v2 above does say “Produces a slightly more stylized result” which would suggest there’s a little more going on under the bonnet and HFv2 was released back in Jan 2024 Topaz Photo AI version 2.3.0 which again may suggest the HFv3 is more refined
Hope this helps
