restore-crop-shifts-to-8x8 unmet unchanged explicit Target quality unmet 34.484 · Time 0.90ms · Grid confidence 1.0000
Target unmet: background-mask-iou
Correct crop-shift-1px, crop-shift-2px, crop-shift-3px and restore the image to 8 x 8 pixels.
auto-quality-prf400-soft-edged-sprite unmet unchanged auto WARNING candidate selection Target quality unmet 12.676 · Time 20982.35ms · Grid confidence 0.5027
Target unmet: exact-image-match, output-size
Process the fixture with Auto and the default settings only, with no case-specific options, and keep the automatic classification, route, and output grid identical to the approved baseline. The target comparison additionally measures how far the output still is from the fixed target image.
remove-background-trim-auto-grid met unchanged explicit Target quality met · Time 1280.48ms · Grid confidence 0.6061
remove the background, trim transparent margins, restore the detected pixel grid.
remove-background-trim-resize-46x13 met unchanged explicit Target quality met · Time 45.01ms · Grid confidence 1.0000
remove the background, trim transparent margins, restore the detected pixel grid, then resize it to 46 x 13 pixels.
trim-auto-grid met unchanged explicit Target quality met · Time 18778.34ms · Grid confidence 0.4907
remove the background, trim transparent margins, restore the detected pixel grid.
remove-inner-background-auto-grid met unchanged explicit Target quality met · Time 8239.99ms · Grid confidence 0.5278
remove the background, trim transparent margins, restore the detected pixel grid.
remove-background-preserve-canvas met unchanged explicit WARNING Target quality met · Time 12174.55ms · Grid confidence 0.5193
remove the background, restore the detected pixel grid.
convert-deterministic-auto-palette met unchanged explicit Target quality met · Time 20.69ms · Grid confidence 1.0000
Keep the image at its original 32 x 32 pixel dimensions and preserve fully transparent pixels while reducing its 947 opaque input colors to an automatically selected eight-color palette with full-strength Ordered dithering.
convert-game-boy-pocket-palette met unchanged explicit Target quality met · Time 280.24ms · Grid confidence 1.0000
Convert a continuous-tone image to the four-color Game Boy Pocket palette without dithering.
convert-monochrome-floyd-steinberg met unchanged explicit Target quality met · Time 201.77ms · Grid confidence 1.0000
Convert the image to monochrome using full-strength Floyd-Steinberg dithering.
remove-background-auto-grid-keep-aspect met unchanged explicit Target quality met · Time 19633.18ms · Grid confidence 0.4907
remove the background, trim transparent margins, restore the detected pixel grid.
pad-wide-image-to-square met unchanged explicit Target quality met · Time 1.50ms · Grid confidence 1.0000
Pad the image to a square canvas without trimming or background removal.
pad-tall-image-to-square met unchanged explicit Target quality met · Time 0.26ms · Grid confidence 1.0000
Pad the image to a square canvas without trimming or background removal.
restore-high-resolution-pixel-grid met unchanged explicit Target quality met · Time 16467.54ms · Grid confidence 0.4695
remove the background, trim transparent margins, restore the detected pixel grid.
preserve-native-pixel-art met unchanged explicit Target quality met · Time 6.16ms · Grid confidence 0.0000
Preserve native-resolution pixel art, including small disconnected components and its limited palette.
restore-nearest-2x-to-8x8 met unchanged explicit Target quality met · Time 20.93ms · Grid confidence 0.7146
Correct nearest-2x.
restore-nearest-3x-to-8x8 met unchanged explicit Target quality met · Time 0.94ms · Grid confidence 1.0000
Correct nearest-3x and restore the image to 8 x 8 pixels.
restore-nearest-4x-to-8x8 met unchanged explicit Target quality met · Time 0.53ms · Grid confidence 1.0000
Correct nearest-4x and restore the image to 8 x 8 pixels.
restore-nearest-8x-to-8x8 met unchanged explicit Target quality met · Time 0.53ms · Grid confidence 1.0000
Correct nearest-8x and restore the image to 8 x 8 pixels.
restore-nearest-16x-to-8x8 met unchanged explicit Target quality met · Time 1.58ms · Grid confidence 1.0000
Correct nearest-16x and restore the image to 8 x 8 pixels.
restore-nearest-32x-to-8x8 met unchanged explicit Target quality met · Time 1.67ms · Grid confidence 1.0000
Correct nearest-32x and restore the image to 8 x 8 pixels.
restore-nearest-1-5x-to-8x8 met unchanged explicit Target quality met · Time 0.31ms · Grid confidence 1.0000
Correct nearest-1.5x and restore the image to 8 x 8 pixels.
restore-nearest-2-5x-to-8x8 met unchanged explicit Target quality met · Time 0.81ms · Grid confidence 1.0000
Correct nearest-2.5x and restore the image to 8 x 8 pixels.
restore-nearest-3-2x-to-8x8 met unchanged explicit Target quality met · Time 0.31ms · Grid confidence 1.0000
Correct nearest-3.2x and restore the image to 8 x 8 pixels.
restore-bilinear-to-8x8 met unchanged explicit Target quality met · Time 99.40ms · Grid confidence 0.4475
Correct bilinear.
restore-bicubic-to-8x8 met unchanged explicit Target quality met · Time 0.99ms · Grid confidence 1.0000
Correct bicubic-equivalent and restore the image to 8 x 8 pixels.
restore-gaussian-blur-to-8x8 met unchanged explicit Target quality met · Time 0.91ms · Grid confidence 1.0000
Correct gaussian-blur-light and restore the image to 8 x 8 pixels.
restore-rgb-noise-to-8x8 met unchanged explicit Target quality met · Time 0.55ms · Grid confidence 1.0000
Correct rgb-noise and restore the image to 8 x 8 pixels.
restore-alpha-edge-blur-to-8x8 met unchanged explicit Target quality met · Time 1.16ms · Grid confidence 1.0000
Correct alpha-edge-blur and restore the image to 8 x 8 pixels.
remove-white-padding-to-8x8 met unchanged explicit Target quality met · Time 2.70ms · Grid confidence 1.0000
Correct padding, background-white and restore the image to 8 x 8 pixels.
remove-black-padding-to-8x8 met unchanged explicit Target quality met · Time 0.85ms · Grid confidence 1.0000
Correct background-black and restore the image to 8 x 8 pixels.
remove-solid-padding-to-8x8 met unchanged explicit Target quality met · Time 0.82ms · Grid confidence 1.0000
Correct background-solid and restore the image to 8 x 8 pixels.
remove-gradient-padding-to-8x8 met unchanged explicit Target quality met · Time 3.96ms · Grid confidence 1.0000
Correct background-gradient and restore the image to 8 x 8 pixels.
restore-anisotropic-scale-to-8x8 met unchanged explicit Target quality met · Time 0.26ms · Grid confidence 1.0000
Correct anisotropic-scale and restore the image to 8 x 8 pixels.
discover-anisotropic-noninteger-grid met unchanged explicit Target quality met · Time 36.54ms · Grid confidence 0.5775
Correct anisotropic-scale, non-integer-scale.
restore-transparent-rgb-padding-to-8x8 met unchanged explicit Target quality met · Time 14.42ms · Grid confidence 0.4587
Correct transparent-rgb-garbage.
withhold-ambiguous-axis-grid met unchanged explicit WARNING Target quality met · Time 3.08ms · Grid confidence 0.0000
Correct one-axis-periodicity.
show-ui-default-candidates met unchanged explicit WARNING candidate selection Target quality met · Time 192.23ms · Grid confidence 0.3241
Correct ambiguous-detail.
restore-soft-edged-sprite-to-34x47 met unchanged explicit Target quality met · Time 1191.12ms · Grid confidence 1.0000
Restore a 1254 x 1254 AI-generated pixel-art-style knight, whose cell boundaries carry antialiasing instead of hard edges, to the hand-given 34 x 47 logical grid, keeping the sword tip, the helmet slits, and the cross on the shield readable as single cells. This output is the target that the Auto case for the same fixture is measured against.
restore-blocky-sprite-to-20x18 met unchanged explicit Target quality met · Time 1184.44ms · Grid confidence 1.0000
Restore a 1254 x 1254 AI-generated slime drawn in 39.7 px blocks to the hand-given 20 x 18 logical grid, keeping the single-cell eye highlight and the one-cell-thick mouth line intact. Reconstruction error alone also accepts a roughly 5x finer reading of the same image, so this output records which of the two scales is the intended one.
restore-alpha-only-grid-to-8x8 met unchanged explicit Target quality met · Time 66.12ms · Grid confidence 0.6213
Correct weak-color-boundaries, alpha-periodicity.
restore-diagonal-grid-to-8x8 met unchanged explicit Target quality met · Time 75.43ms · Grid confidence 0.4401
Correct diagonal-dominant.
prefer-base-grid-over-doubled-period met unchanged explicit Target quality met · Time 60.25ms · Grid confidence 0.6661
Correct same-color-runs, doubled-period.
restore-thin-features-and-alpha-coverage met unchanged explicit Target quality met · Time 4.31ms · Grid confidence 1.0000
Restore area-coverage alpha from enlarged artwork containing thin lines and highlights, while selecting an input RGB without mixing in hidden colors from transparent pixels.
convert-continuous-tone-balanced met unchanged explicit Target quality met · Time 147.98ms · Grid confidence 1.0000
Route a 48 x 32 continuous-tone image through Auto to the Convert pipeline, derive three candidate resolutions from its aspect ratio and information density, and emit the balanced candidate at 24 x 16 with edge-aware resampling instead of restoring an original grid.
convert-illustration-detailed met unchanged explicit Target quality met · Time 46.25ms · Grid confidence 1.0000
Convert a 72 x 48 illustration with transparent margins and thin high-contrast lines to the detailed candidate at 54 x 36, keeping fully transparent pixels transparent and never picking the RGB of a nearly transparent pixel as a cell's representative color.
remove-gradient-background-with-border-model met unchanged explicit WARNING Target quality met · Time 7.10ms · Grid confidence 1.0000
Correct background-gradient.
share-balanced-palette-across-batch met unchanged explicit Target quality met · Time 18.91ms · Grid confidence 1.0000
Correct low-color-subject.
retain-protected-small-details met unchanged explicit WARNING Target quality met · Time 1.18ms · Grid confidence 1.0000
Remove isolated background noise while retaining paired eyes, dakuten, and disconnected star and spark details in native-resolution pixel art.
remove-isolated-small-noise met unchanged explicit WARNING Target quality met · Time 0.56ms · Grid confidence 1.0000
Remove a weak isolated one-pixel noise component from a uniform background without changing the main native-resolution subject.
skip-small-removal-on-uncertain-background met unchanged explicit WARNING Target quality met · Time 1.52ms · Grid confidence 1.0000
Keep every pixel unchanged when automatic background confidence is too low to safely classify disconnected details as removable noise.
guide-recipe1-knight-sprite met unchanged explicit Target quality met · Time 16976.94ms · Grid confidence 0.5468
Process the 2048 x 2048 AI-generated knight published in the recipes guide, whose cell boundaries are antialiased over a magenta background, with the Best Match preset the page tells the reader to select, and reproduce the published 60 x 85 result pixel for pixel. A mismatch means the published image no longer follows from the published steps.
guide-recipe2-potion-icon met unchanged explicit Target quality met · Time 21950.90ms · Grid confidence 0.5570
Process the 2752 x 1536 AI-generated potion bottle published in the recipes guide, drawn over a chroma-key green background, with the Transparent Icon preset the page tells the reader to select, and reproduce the published 16 x 23 result pixel for pixel, including the transparent background.
guide-recipe3-dragon-sprite met unchanged explicit Target quality met · Time 32125.63ms · Grid confidence 0.5362
Process the 2816 x 1536 AI-generated green dragon published in the recipes guide, drawn over a red background, with the Retro Game Style preset the page tells the reader to select, and reproduce the published 44 x 47 result pixel for pixel, including the four-tone palette the conversion replaces the generated colors with.
guide-recipe4-landscape met unchanged explicit Target quality met · Time 16642.97ms · Grid confidence 0.5272
Process the 2752 x 1536 AI-generated mountain landscape published in the recipes guide, whose pixel cells are softened by generation, with the Background Artwork preset the page tells the reader to select, and reproduce the published 256 x 144 result pixel for pixel without making any part of the full-frame scenery transparent.
guide-recipe5-chibi-character met unchanged explicit Target quality met · Time 3068.60ms · Grid confidence 1.0000
Process the 2816 x 1536 AI-generated chibi character published in the recipes guide, an ordinary flat-colored illustration rather than pixel art, with the Convert Illustration to Pixel Art preset the page tells the reader to select, and reproduce the published 60 x 81 result pixel for pixel, including the transparent background and the thick outlines carried over from the illustration.
auto-auto-grid-detection met unchanged auto Target quality met · Time 20688.37ms · Grid confidence 0.4961
Process the fixture with Auto and the default settings only, with no case-specific options, and keep the automatic classification, route, and output grid identical to the approved baseline. The target comparison additionally measures how far the output still is from the fixed target image.
auto-high-resolution met unchanged auto Target quality met · Time 16736.30ms · Grid confidence 0.4691
Process the fixture with Auto and the default settings only, with no case-specific options, and keep the automatic classification, route, and output grid identical to the approved baseline. The target comparison additionally measures how far the output still is from the fixed target image.
auto-inner-background-removal met unchanged auto WARNING candidate selection Target quality met · Time 11932.43ms · Grid confidence 0.5334
Process the fixture with Auto and the default settings only, with no case-specific options, and keep the automatic classification, route, and output grid identical to the approved baseline. The target comparison additionally measures how far the output still is from the fixed target image.
auto-no-trimming met unchanged auto Target quality met · Time 14056.42ms · Grid confidence 0.5285
Process the fixture with Auto and the default settings only, with no case-specific options, and keep the automatic classification, route, and output grid identical to the approved baseline. The target comparison additionally measures how far the output still is from the fixed target image.
auto-quality-prf400-ambiguous-grid-scale met unchanged auto Target quality met · Time 17020.89ms · Grid confidence 0.5819
Process the fixture with Auto and the default settings only, with no case-specific options, and keep the automatic classification, route, and output grid identical to the approved baseline. The target comparison additionally measures how far the output still is from the fixed target image.
auto-resize-and-remove-bg met unchanged auto Target quality met · Time 6155.13ms · Grid confidence 0.6268
Process the fixture with Auto and the default settings only, with no case-specific options, and keep the automatic classification, route, and output grid identical to the approved baseline. The target comparison additionally measures how far the output still is from the fixed target image.
auto-resize-with-trimming met unchanged auto Target quality met · Time 1734.26ms · Grid confidence 0.4538
Process the fixture with Auto and the default settings only, with no case-specific options, and keep the automatic classification, route, and output grid identical to the approved baseline. The target comparison additionally measures how far the output still is from the fixed target image.
