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 3 of 358; 24 results per page.

Show the canonical directory

A av f5: dense pose map

A dense pose map for the published plate a-av-f5.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

A av f5: depth map

A depth map for the published plate a-av-f5.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 87.9% 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

A av f5: expanded canvas

The same view of head and shoulders portrait of an east asian woman with glasses, plain warm grey background, expanded to 512x768 - 128 pixels added above and below, the symmetric case turned on its side - so 33.3% of this frame is invented canvas. The original sits at pixels 0,128 to 512,640. Compare it INSET by 40 pixels: over that core it differs from the original by only 5.482/255, the VAE round trip, but over the whole rectangle by 6.4/255, 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 · 512 × 768 px
Use case: Inpainting· Conversion set

A av f5: frame before expansion

A 512x512 view of head and shoulders portrait of an east asian woman with glasses, plain warm grey background - the frame an outpainting tool is given, cropped from the published plate nss-a-av-f5_00001_.png. Its companion expands it to 512x768 with 128 pixels added above and below, the symmetric case turned on its side, 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

A av f5: outpaint boundary record

Where the original view of head and shoulders portrait of an east asian woman with glasses, plain warm grey background landed inside the expanded frame, as JSON: the rectangle 0,128 to 512,640 in a 512x768 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

A av f5: surface normal map

A tangent-space surface normal map for the published plate a-av-f5.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 0.9959, 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

A av m3: canny edge map

A canny edge map for the published plate a-av-m3.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 4.4% 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

A av m3: dense pose map

A dense pose map for the published plate a-av-m3.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

A av m3: depth map

A depth map for the published plate a-av-m3.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 97.3% 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

A av m3: expanded canvas

The same view of head and shoulders portrait of a bearded white man in his thirties, plain olive studio background, expanded to 704x512 - 192 pixels added to the right alone, so the original is no longer centred - so 27.3% of this frame is invented canvas. The original sits at pixels 0,0 to 512,512. Compare it INSET by 40 pixels: over that core it differs from the original by only 5.277/255, the VAE round trip, but over the whole rectangle by 6.19/255, 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 × 512 px
Use case: Inpainting· Conversion set

A av m3: frame before expansion

A 512x512 view of head and shoulders portrait of a bearded white man in his thirties, plain olive studio background - the frame an outpainting tool is given, cropped from the published plate nss-a-av-m3_00001_.png. Its companion expands it to 704x512 with 192 pixels added to the right alone, so the original is no longer centred, 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

A av m3: outpaint boundary record

Where the original view of head and shoulders portrait of a bearded white man in his thirties, plain olive studio background landed inside the expanded frame, as JSON: the rectangle 0,0 to 512,512 in a 704x512 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

A av m3: surface normal map

A tangent-space surface normal map for the published plate a-av-m3.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 0.9966, 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

A av m4: canny edge map

A canny edge map for the published plate a-av-m4.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 4.7% 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

A av m4: dense pose map

A dense pose map for the published plate a-av-m4.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

A av m4: depth map

A depth map for the published plate a-av-m4.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 99.7% 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

A av m4: expanded canvas

The same view of head and shoulders portrait of a south asian man in his fifties, plain slate studio background, expanded to 704x512 - 192 pixels added to the left alone, so the original's origin moves - so 27.3% of this frame is invented canvas. The original sits at pixels 192,0 to 704,512. Compare it INSET by 40 pixels: over that core it differs from the original by only 6.007/255, the VAE round trip, but over the whole rectangle by 5.68/255, 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 × 512 px
Use case: Inpainting· Conversion set

A av m4: frame before expansion

A 512x512 view of head and shoulders portrait of a south asian man in his fifties, plain slate studio background - the frame an outpainting tool is given, cropped from the published plate nss-a-av-m4_00001_.png. Its companion expands it to 704x512 with 192 pixels added to the left alone, so the original's origin moves, 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

A av m4: outpaint boundary record

Where the original view of head and shoulders portrait of a south asian man in his fifties, plain slate studio background landed inside the expanded frame, as JSON: the rectangle 192,0 to 704,512 in a 704x512 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

A av m4: reconstructed mesh (GLB)

A single-image 3D reconstruction of head and shoulders portrait of a south asian man in his fifties, 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 28,536 vertices and 57,064 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 0.3191 x 1.0247 x 0.8981 units.

File: GLB · Mesh · 57,064 triangles
Use case: Mesh processing QA· Paired fixture

A av m4: reconstructed mesh (OBJ)

A single-image 3D reconstruction of head and shoulders portrait of a south asian man in his fifties, 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 28,536 vertices and 57,064 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 0.3191 x 1.0247 x 0.8981 units.

File: OBJ · Mesh · 57,064 triangles
Use case: Mesh processing QA· Paired fixture

A av m4: surface normal map

A tangent-space surface normal map for the published plate a-av-m4.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 0.9963, 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

A av m5: canny edge map

A canny edge map for the published plate a-av-m5.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 1.5% 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

A av m5: dense pose map

A dense pose map for the published plate a-av-m5.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