UniFab Upscale Mode: No CABAC, Baseline Profile - Quality Worse Than Denoise+4K

kontakt2181157

Hello everyone,

I’m encountering a strange behavior with UniFab in Upscale mode and wanted to share my findings.

My workflow:

Deinterlace

Stabilize

Denoise

The intermediate result after the Denoise step has a High profile with CABAC – technically flawless.

When I then upscale from 1080p to 4K using the Enquoix model (with the best available output settings), the file does get upscaled, but the image quality is worse compared to another workflow.

The better workflow:
If I take the file after Stabilization and process it directly in Denoise mode, setting the output resolution to 4K, I get a significantly better result – without even using the dedicated Upscale mode.

The issue clearly lies in the encoder parameters, not in the AI itself.

The Enquoix model (pure Upscale) forces the encoder into the 20-year-old Baseline mode – a compatibility-only mode without CABAC and without B-frames. This wastes 30–40% more bitrate to achieve the same quality.

The Denoise+4K model (Denoise + Upscale) on the other hand delivers at least Main@L5.1 with CABAC. That’s the bare minimum for modern, efficient HD/4K encoding. As a result, it can show noticeably more detail at 61 Mbps than the pure Upscale mode at just 53 Mbps – despite using only a little more bitrate, because the data is distributed far more intelligently.

From my logs:

Enquoix base model (Upscale only):
Log shows: encoder library used : x264 core 164 (software encoder).
Parameters: rc=cbr and cabac=0 → Constrained Baseline without CABAC.

Denoise+4K model (Denoise + Upscale):
Log shows: CUDA GPU acceleration for video H264 encoding enabled – the NVIDIA hardware encoder (NVENC) is used.
The hardware encoder is extremely fast but usually inferior to software x264 in compression efficiency.
HOWEVER: In my case, NVENC still delivered the Main@L5.1 profile with CABAC – while the software x264 remained stuck on the primitive Constrained Baseline (no CABAC).

With these results, one has to ask: What’s the point of a separate Upscale mode and so many different models, if the integrated Denoise mode (with 4K output) gives better results?

The root cause is clearly the encoder profiles that UniFab enforces in Upscale mode – not the AI models themselves.

Has anyone had similar experiences or found a solution?
Is there any way to manually force the High profile with CABAC in Upscale mode?

Thanks

Adventurer

Thank you for providing such detailed information about your testing workflow, log data, and comparison results.

According to your description, when using the Enquoix model in the standalone Upscale mode, the output file is encoded with the x264 software encoder. However, the log shows that CABAC is disabled and the Constrained Baseline Profile is used. In contrast, when outputting directly to 4K through Denoise mode, NVIDIA NVENC is enabled and the resulting file uses Main@L5.1 with CABAC.

You also observed that the latter workflow preserves noticeably more image detail even though the bitrate is only slightly higher. Based on this, you suspect that the encoder settings currently used in Upscale mode may be affecting the final image quality and compression efficiency.

To help our technical team investigate this issue further, please provide the following information:

The complete logs for the relevant tasks
Screenshots of the output settings used in both workflows
The full UniFab version number
Your graphics card model and driver version

If possible, please also provide a short source file that can be used to reproduce the issue, or short output samples generated by each workflow.

We will forward your feedback regarding the encoder profile, CABAC settings, and the inconsistent encoder behavior between different processing modes to our technical team for further analysis.

As for whether High Profile, CABAC, or other advanced encoder parameters can be manually specified in Upscale mode, this will need to be confirmed by our technical team based on the current product design. At this time, we are unable to confirm whether this option is supported.

Until we receive further findings, you may continue using Denoise mode with the output resolution set to 4K as a temporary workaround, since this workflow currently provides better image quality in your tests.

Thank you again for your thorough testing and detailed feedback. The log comparisons and technical analysis you provided will be very helpful in identifying the cause of the issue.