Edges models
8 edges models. Each section says what the model is, whether it may be used commercially and how fast it is; licences and checks are under Details.
Input: one RGB image. Output: a line / edge map [H, W] in [0, 1] at the input size (1 = line), the ControlNet preprocessors (line art, HED, PiDiNet, TEED / Anyline); M-LSD also returns straight line segments.
Measured on RTX 5060 Ti, torch 2.14.1+cu130; fastforks bench MODEL --size HxW measures yours. The summary uses one input, 1080x1920: kernels time with its speed-up over the faster original run, and kernels peak reserved memory with its ratio to the smaller original one. Where measured (one variant per family), a variant's table also lists portable under torch.compile and the fp16 TensorRT engine of portable (export; memory: the engine's device memory + torch's peak). – = not measured; no kernels = the family has no kernels backend (reason under its table). Reserved memory is the allocator's cache: kernels (CUDA graphs, cuDNN workspaces) can reserve a few percent to some tens of percent more than portable at the same allocated peak.
Other devices: Apple M1 Pro 16 GB, NVIDIA L4, NVIDIA L40S, NVIDIA A10, NVIDIA A100-SXM4-40GB, NVIDIA RTX PRO 6000; across devices.
| model | commercial |
|---|---|
anyline | yes |
hed | yes |
lineart | yes |
lineart-anime | yes |
lineart-coarse | yes |
mlsd | yes |
pidinet | no |
teed | yes |
All models
Modes, licences, training data and outputs per model
Commercial status per variant: yes if the code and the weights licence both allow commercial use (the training data is listed but does not change it; weights without a licence of their own are assumed to carry the code licence); no if either forbids it; unclear for custom licence terms (treat as no).
| model | modes | code licence | weights licence | training data | commercial | outputs |
|---|---|---|---|---|---|---|
anyline | portable, kernels | MIT | LicenseRef-CreativeML-OpenRAIL-PlusPlus-M | unstated | yes | edges |
hed | portable, kernels | Apache-2.0 | Apache-2.0 | unstated | yes | edges |
lineart | portable, kernels | MIT | MIT (assumed from code) | unstated | yes | edges |
lineart-anime | portable, kernels | MIT | MIT (assumed from code) | unstated | yes | edges |
lineart-coarse | portable, kernels | MIT | MIT (assumed from code) | unstated | yes | edges |
mlsd | portable, kernels | Apache-2.0 | Apache-2.0 | unstated | yes | edges, lines |
pidinet | portable, kernels | LicenseRef-research-only | LicenseRef-research-only (assumed from code) | unstated | no (code: LicenseRef-research-only (noncommercial); weights: LicenseRef-research-only (assumed from code)) | edges |
teed | portable, kernels | MIT | MIT | biped | yes | edges |
Training datasets
| id | dataset | licence | commercial use |
|---|---|---|---|
biped | BIPED (Barcelona Images for Perceptual Edge Detection) | LicenseRef-research-only | no |