Images are the most-tested files of all, yet generic sample sites hand you a photo with no documented properties. Here, every image records exactly what it is. Denoise, restoration, inpaint, deblur, upscale, colourization, watermark, outpaint, style-transfer, and enhance suites pair degraded inputs with clean references. Segmentation masks, visual-diff twins, EXIF/ICC ladders, multipage sprites, chart-vision, codec ladders, OCR hardcases, and soft-edge matting extend the set for modern vision QA. Clean ↔ noisy and colour ↔ greyscale pairs make before/after testing trivial.
Filter images on Browse · 2343 files · 41 subcategories
Results start with a representative from each related test family. Use a card’s variant menu or the filters below to reach a specific format, profile, or failure case; every sample retains its own detail page and download.
Use the media style and subject filters below to find realistic examples, or open realism, grouped by subject.
Every image ships with documented specs (dimensions, seeds, damage type, pair/group IDs). Denoise, restoration, colourization, watermark, and enhance suites include clean ground-truth twins so you can score tools with PSNR/SSIM instead of guessing.
No. Face-restore fixtures use synthetic illustrations, and watermark suites use SAMPLE logos/text only. Corrupt samples are labelled intentionally corrupt.
Open any suite member and use the Pair / Group links on the file page, or filter Browse by purpose (for example colourization-testing or watermark-removal-testing).
Wave E adds segmentation scene/mask/JSON triples, A/B diff-regression twins, EXIF Orientation + ICC colour notes, multipage TIFF / sprite / favicon packs, chart-as-image mocks, codec quality ladders, hard OCR cases, and soft-alpha matting hardcases.
Start with one example from each use-case group, then continue through its other test families. Choose a use case, search, or filter to find a specific profile; a card’s variant menu contains its related samples.
927 test families · 2343 available files · Page 1 of 52
Ai Segmentation · Synthetic realistic media
A dense pose map for the published plate a-av-f3.png, 512x512. DensePose body-part segmentation, which labels regions of every person it finds rather than returning a skeleton, so background figures are labelled as well
Derived from an AI-generated plate. Synthetic, not a photograph of a real scene.
Ai Vision · Synthetic realistic media
A canny edge map for the published plate a-av-f3.png, 1024x1024. Canny edge detection at low threshold 0.1 and high 0.3, run at the plate's own resolution so the edges land on the same pixels as the photograph they came
Derived from an AI-generated plate. Synthetic, not a photograph of a real scene.
Avatar
A 256×256 identicon-style avatar generated deterministically from the seed “ada-lovelace”: a symmetric 5×5 block pattern like the default avatars on many sites. For testing avatar rendering, placeholder generation, and i
Background Removal
A left-to-right alpha gradient over a solid colour, for testing how a viewer or compositor renders partial transparency.
Business Kits
Operating chart PNG for Alder Books Reconciliation. A 1440 by 900 RGB chart with 24 labeled source-derived observations in USD.
Chart Vision
Synthetic dashboard mock (KPI cards + bar chart): SAMPLE UI for layout / chart vision models. Not a real product.
Charts
A clean bar chart of monthly revenue with axis labels, gridlines, and value labels: a real-world fixture for testing chart-extraction and OCR tools, vision models, and thumbnail rendering.
Codec Ladder
Same blocks scene encoded as png: rung on the Wave E codec ladder for quality / convert comparisons.
Color And Metadata
A 16-bit (deep-colour) grayscale PNG holding a smooth 0–65535 gradient, for testing high-bit-depth support and spotting banding when a tool truncates to 8-bit.
Colourize Set
Greyscale input for colourizing the fruit scene. Pair with the colour ground truth in this group.
Comfy Realism · Synthetic realistic media
A synthetic photographic plate of an independent business owner, 701x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate owner-cafe.
AI-generated / synthetic. Not a photograph of a real person, place or event.
Conditioning Maps
Colour ground-truth for the apple conditioning suite. Every map in this group is derived from this exact image, so a guided model's output can be scored against it.
Deblur Set
Clean reference for deblur base A. Compare deblurred outputs of the blurred variants in this group against this file.
Denoise Set
The clean reference image for denoise base A: a fruit still life on studio white. Diff the noisy variants in this set against this file to measure filter accuracy.
Diff Regression
Baseline twin A for visual-diff regression (pixel change suite: 1px-crop). Compare against twin B.
Edge Cases
An 8-frame looping animated GIF of a moving dot. Tests animation handling, first-frame extraction, and GIF parsing.
Enhance Set
Clean fruit still life for a second enhancement ladder subject.
EXIF Icc
JPEG with EXIF Orientation=2 (flip-h). Pixels are upright: viewers/tools should apply the tagged transform. SAMPLE fixture.
The use-case group filter replaces the long list of category sections.
