comparisons/README.md

Image comparison gallery

All comparison pictures are actual recorded inference outputs. Each stack contains labeled full frames, identical 1:1 crops and absolute RGB differences amplified eight times. Metrics apply to full-resolution images, not previews.

Comparison	Viewer	Image stack	Native detail crops
2K product: BF16 tuning, Q8, Q4, three-pass preview	Open	Frames	Details
2K portrait: native BF16 vs Q8	Open	Frames	Details
Same final latent: VAE batches 1, 4, 8, 16	Open	Frames	Details
Saved CUDA BF16 vs MLX, product	Open	Frames	Details
Saved CUDA BF16 vs MLX, portrait	Open	Frames	Details
Saved CUDA BF16 vs MLX, native 4K	Open	Frames	Details

The editing demonstration places the input reference beside the native MLX emerald-glass edit. It is a functional example, not a pixel-similarity comparison.

The CUDA comparison uses the original saved RTX 5090 BF16 run with upstream quality=lossless. Its hardware and decoder quality setting differ from the MLX native tile recipe. It provides visual context; it does not isolate port error or establish a same-hardware speedup.

The default MLX BF16 output is the reference for the quantization/tuning comparisons. Q8, Q4, fused kernels and fewer steps change its pixels. Read the experiment report before selecting a profile.

Full-resolution Mac outputs and trace tensors are retained locally under outputs/suite/ (ignored by Git). Source hashes, configuration, memory and timing records are exported under reports/inference/ and each gallery's metrics.json. Original model weights are not included.