Explore the test library

Find files, editable templates and browser test targets by what you need to make or test. The directory below is cut by format; the two collections under it cut the same library by subject and by workflow.

Filter the library

SearchTypeCategorySubcategoryFormatUse caseIndustryWorkflowValidityEditable workspaceDestination platformBrowser test targetSort

8584 results

Page 5 of 358; 24 results per page.

Show the canonical directory

png

4.8 KB

A avatar f2: dense pose map

A dense pose map for the published plate a-avatar-f2.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 as the subject. Lit coverage measures 100.0% of the frame. The plate and this map are the same scene at the same size, so they can be compared pixel for pixel rather than by eye.

File: PNG · Ai Segmentation · 512 × 512 px
Use case: Pose estimation

png

160.1 KB

A avatar f2: depth map

A depth map for the published plate a-avatar-f2.png, 1024x1024. Monocular depth from Depth Anything V2 (vitl), rendered at the plate's long edge rather than the 512-pixel default, so depth and colour can be compared per pixel without a resample in between. Lit coverage measures 92.3% of the frame. The plate and this map are the same scene at the same size, so they can be compared pixel for pixel rather than by eye.

File: PNG · Ai Vision · 1024 × 1024 px
Use case: Depth estimation

png

652.5 KB

A avatar f2: expanded canvas

The same view of head and shoulders portrait of a young hijabi woman against a plain neutral studio background, expanded to 704x704 - 96 pixels added on all four sides - so 47.1% of this frame is invented canvas. The original sits at pixels 96,96 to 608,608. Compare it INSET by 40 pixels: over that core it differs from the original by only 5.267/255, the VAE round trip, but over the whole rectangle by 9.706/255, because the pad deliberately feathers the original's outer edge into the new area. A test that expects the whole rectangle untouched fails on a correct tool.

File: PNG · Outpaint Borders · 704 × 704 px
Use case: Inpainting· Conversion set

png

418.6 KB

A avatar f2: frame before expansion

A 512x512 view of head and shoulders portrait of a young hijabi woman against a plain neutral studio background - the frame an outpainting tool is given, cropped from the published plate nss-a-avatar-f2_00001_.png. Its companion expands it to 704x704 with 96 pixels added on all four sides, and the boundary record in this group states the exact rectangle this image occupies inside that frame - so where it ended up can be checked rather than eyeballed.

File: PNG · Outpaint Borders · 512 × 512 px
Use case: Inpainting· Conversion set

json

828 B

A avatar f2: outpaint boundary record

Where the original view of head and shoulders portrait of a young hijabi woman against a plain neutral studio background landed inside the expanded frame, as JSON: the rectangle 96,96 to 608,608 in a 704x704 canvas, the padding that produced it, and the 40-pixel feather that means the comparison must be inset. Authored BEFORE the expansion ran, so it is ground truth rather than a rectangle recovered afterwards by matching the original against the result - which is what a consumer would otherwise have to do, and which cannot distinguish a correct offset from a plausible one.

File: JSON · Outpaint Borders
Use case: Inpainting· Conversion set

glb

1.7 MB

A avatar f2: reconstructed mesh (GLB)

A single-image 3D reconstruction of head and shoulders portrait of a young hijabi woman against a plain neutral studio background, written as binary glTF, geometry addressed through an accessor table. Its twin in this group is the same mesh written as the other format, from ONE reconstruction rather than two runs - so the pair tests whether a reader returns the same geometry from two containers with nothing in common. Both hold 29,272 vertices and 58,536 triangles; those counts were read from the GLB's accessor table and by counting lines in the OBJ, by separate code, and a disagreement would have stopped this shipping. It is closed: every edge belongs to exactly two triangles, so there are no holes and no non-manifold edges. The bounding box measures 0.2703 x 1.0417 x 0.9562 units.

File: GLB · Mesh · 58,536 triangles
Use case: Mesh processing QA· Paired fixture

obj

4.6 MB

A avatar f2: reconstructed mesh (OBJ)

A single-image 3D reconstruction of head and shoulders portrait of a young hijabi woman against a plain neutral studio background, written as Wavefront text, one `v` line per vertex and one `f` line per face. Its twin in this group is the same mesh written as the other format, from ONE reconstruction rather than two runs - so the pair tests whether a reader returns the same geometry from two containers with nothing in common. Both hold 29,272 vertices and 58,536 triangles; those counts were read from the GLB's accessor table and by counting lines in the OBJ, by separate code, and a disagreement would have stopped this shipping. It is closed: every edge belongs to exactly two triangles, so there are no holes and no non-manifold edges. The bounding box measures 0.2703 x 1.0417 x 0.9562 units.

File: OBJ · Mesh · 58,536 triangles
Use case: Mesh processing QA· Paired fixture

png

450.5 KB

A avatar f2: surface normal map

A tangent-space surface normal map for the published plate a-avatar-f2.png, 1024x1024 - the same size as the plate, so the two compare pixel for pixel with no resample in between. RGB encodes the XYZ surface direction remapped from -1..1 into 0..255. Decoded back to vectors this file measures a mean length of 0.9968, which is the number to check your own decode against: a reader that transposes the channels or inverts the remap still produces a plausible-looking image, and lights the surface the wrong way.

File: PNG · Ai Vision · 1024 × 1024 px
Use case: PBR material testing

png

23.9 KB

A avatar m1: canny edge map

A canny edge map for the published plate a-avatar-m1.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 from. Lit coverage measures 1.4% of the frame. The plate and this map are the same scene at the same size, so they can be compared pixel for pixel rather than by eye.

File: PNG · Ai Vision · 1024 × 1024 px
Use case: Edge detection

png

359.3 KB

A avatar m1: clean plate (ground truth)

A clean 512x512 crop of head and shoulders portrait of a smiling black man against a plain grey studio background, taken from the published plate a-avatar-m1.png before anything was added to it. This is the ANSWER KEY for its group: the object in the source file was composited onto this image, so this is exactly what was behind it. Nothing else in the group came from a second tool's guess.

File: PNG · Inpaint Cuts · 512 × 512 px
Use case: Inpainting· Conversion set

png

4.5 KB

A avatar m1: dense pose map

A dense pose map for the published plate a-avatar-m1.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 as the subject. Lit coverage measures 100.0% of the frame. The plate and this map are the same scene at the same size, so they can be compared pixel for pixel rather than by eye.

File: PNG · Ai Segmentation · 512 × 512 px
Use case: Pose estimation

png

125 KB

A avatar m1: depth map

A depth map for the published plate a-avatar-m1.png, 1024x1024. Monocular depth from Depth Anything V2 (vitl), rendered at the plate's long edge rather than the 512-pixel default, so depth and colour can be compared per pixel without a resample in between. Lit coverage measures 80.6% of the frame. The plate and this map are the same scene at the same size, so they can be compared pixel for pixel rather than by eye.

File: PNG · Ai Vision · 1024 × 1024 px
Use case: Depth estimation

png

364.7 KB

A avatar m1: object composited in

The same view of head and shoulders portrait of a smiling black man against a plain grey studio background, with a foreign object composited over 5.29% of the frame as a single organic region, neither a rectangle nor an ellipse. This is the file an object-removal tool is given. Outside the mask it is byte-identical to the clean plate beside it, so any difference a tool leaves there is damage it did rather than content it was handed.

File: PNG · Inpaint Cuts · 512 × 512 px
Use case: Inpainting· Conversion set

png

349.8 KB

A avatar m1: object removed

Head and shoulders portrait of a smiling black man against a plain grey studio background, with the object taken back out by Stable Diffusion 1.5 inpainting and the gap reconstructed from the surrounding context alone - the masked latents are erased before sampling, so the model never saw what it was painting over. Inside the mask it differs from the source by 54.279/255 and from the ground-truth plate by 10.905/255; the second number is NOT expected to be small, because an inpainter invents plausible content rather than recovering what was there. Beyond a 16-pixel ring around the mask the frame changes by only 4.019/255, which is the full-frame VAE round trip and not an edit.

File: PNG · Inpaint Cuts · 512 × 512 px
Use case: Inpainting· Conversion set

glb

2 MB

A avatar m1: reconstructed mesh (GLB)

A single-image 3D reconstruction of head and shoulders portrait of a smiling black man against a plain grey studio background, written as binary glTF, geometry addressed through an accessor table. Its twin in this group is the same mesh written as the other format, from ONE reconstruction rather than two runs - so the pair tests whether a reader returns the same geometry from two containers with nothing in common. Both hold 34,562 vertices and 69,120 triangles; those counts were read from the GLB's accessor table and by counting lines in the OBJ, by separate code, and a disagreement would have stopped this shipping. It is closed: every edge belongs to exactly two triangles, so there are no holes and no non-manifold edges. The bounding box measures 0.1821 x 1.032 x 1.0028 units.

File: GLB · Mesh · 69,120 triangles
Use case: Mesh processing QA· Paired fixture

obj

5.5 MB

A avatar m1: reconstructed mesh (OBJ)

A single-image 3D reconstruction of head and shoulders portrait of a smiling black man against a plain grey studio background, written as Wavefront text, one `v` line per vertex and one `f` line per face. Its twin in this group is the same mesh written as the other format, from ONE reconstruction rather than two runs - so the pair tests whether a reader returns the same geometry from two containers with nothing in common. Both hold 34,562 vertices and 69,120 triangles; those counts were read from the GLB's accessor table and by counting lines in the OBJ, by separate code, and a disagreement would have stopped this shipping. It is closed: every edge belongs to exactly two triangles, so there are no holes and no non-manifold edges. The bounding box measures 0.1821 x 1.032 x 1.0028 units.

File: OBJ · Mesh · 69,120 triangles
Use case: Mesh processing QA· Paired fixture

png

1.1 KB

A avatar m1: removal mask

The exact footprint of the object sitting over head and shoulders portrait of a smiling black man against a plain grey studio background, as an 8-bit mask covering 5.29% of the frame as a single organic region, neither a rectangle nor an ellipse. It holds only the values 0 and 255. The footprint is what DREW the object, so it is ground truth by construction rather than a segmentation of it. Hard-edged on purpose: a feathered edge has no exact footprint, and the exactness is the point of shipping it.

File: PNG · Inpaint Cuts · 512 × 512 px
Use case: Inpainting· Conversion set

png

433.7 KB

A avatar m1: surface normal map

A tangent-space surface normal map for the published plate a-avatar-m1.png, 1024x1024 - the same size as the plate, so the two compare pixel for pixel with no resample in between. RGB encodes the XYZ surface direction remapped from -1..1 into 0..255. Decoded back to vectors this file measures a mean length of 0.9971, which is the number to check your own decode against: a reader that transposes the channels or inverts the remap still produces a plausible-looking image, and lights the surface the wrong way.

File: PNG · Ai Vision · 1024 × 1024 px
Use case: PBR material testing

png

60 KB

A avatar m2: canny edge map

A canny edge map for the published plate a-avatar-m2.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 from. Lit coverage measures 4.5% of the frame. The plate and this map are the same scene at the same size, so they can be compared pixel for pixel rather than by eye.

File: PNG · Ai Vision · 1024 × 1024 px
Use case: Edge detection

png

5.2 KB

A avatar m2: dense pose map

A dense pose map for the published plate a-avatar-m2.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 as the subject. Lit coverage measures 100.0% of the frame. The plate and this map are the same scene at the same size, so they can be compared pixel for pixel rather than by eye.

File: PNG · Ai Segmentation · 512 × 512 px
Use case: Pose estimation

png

145.6 KB

A avatar m2: depth map

A depth map for the published plate a-avatar-m2.png, 1024x1024. Monocular depth from Depth Anything V2 (vitl), rendered at the plate's long edge rather than the 512-pixel default, so depth and colour can be compared per pixel without a resample in between. Lit coverage measures 99.4% of the frame. The plate and this map are the same scene at the same size, so they can be compared pixel for pixel rather than by eye.

File: PNG · Ai Vision · 1024 × 1024 px
Use case: Depth estimation

png

637.8 KB

A avatar m2: expanded canvas

The same view of head and shoulders portrait of an older east asian man against a plain warm studio background, expanded to 768x640 - a different amount on every side, which is the case a tool assuming symmetry fails - so 46.7% of this frame is invented canvas. The original sits at pixels 64,32 to 576,544. Compare it INSET by 40 pixels: over that core it differs from the original by only 5.021/255, the VAE round trip, but over the whole rectangle by 8.184/255, because the pad deliberately feathers the original's outer edge into the new area. A test that expects the whole rectangle untouched fails on a correct tool.

File: PNG · Outpaint Borders · 768 × 640 px
Use case: Inpainting· Conversion set

png

395.8 KB

A avatar m2: frame before expansion

A 512x512 view of head and shoulders portrait of an older east asian man against a plain warm studio background - the frame an outpainting tool is given, cropped from the published plate nss-a-avatar-m2_00001_.png. Its companion expands it to 768x640 with a different amount on every side, which is the case a tool assuming symmetry fails, and the boundary record in this group states the exact rectangle this image occupies inside that frame - so where it ended up can be checked rather than eyeballed.

File: PNG · Outpaint Borders · 512 × 512 px
Use case: Inpainting· Conversion set

json

828 B

A avatar m2: outpaint boundary record

Where the original view of head and shoulders portrait of an older east asian man against a plain warm studio background landed inside the expanded frame, as JSON: the rectangle 64,32 to 576,544 in a 768x640 canvas, the padding that produced it, and the 40-pixel feather that means the comparison must be inset. Authored BEFORE the expansion ran, so it is ground truth rather than a rectangle recovered afterwards by matching the original against the result - which is what a consumer would otherwise have to do, and which cannot distinguish a correct offset from a plausible one.

File: JSON · Outpaint Borders
Use case: Inpainting· Conversion set