M-LSD line segments (fastforks)

Mobile line segment detector (Gu et al., AAAI 2022; controlnet_aux MLSDdetector, ComfyUI's "M-LSD Lines"): a MobileNetV2 network that predicts segment centers and end-point displacements; returns the straight segments and the 1-pixel line map ControlNet's MLSD model takes.

This repo is the model card only: it holds no weights. fastforks downloads the authors' weights from the links below and checks them against the SHA-256 in the model card. Code: https://github.com/kleinicke/fastforks. Kernels for the kernels backend: https://huggingface.co/fastforks/kernels. Original code: https://github.com/huggingface/controlnet_aux at b1aac318b15c.

Task: edges. Tier: experimental. Outputs: edges, lines. Backends: portable.

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.

Variants

Weights are the authors' files (not hosted here). SHA-256 shortened to 12 hex digits; the full hashes are in card.toml.

variant weights (author link) SHA-256 weights licence commercial use
mlsd@1 mlsd_large_512_fp32.pth 5696f168eb2c Apache-2.0 yes

Licence

Original-code strings, recorded as they are (research-use package; check them before any other use). Code: Apache-2.0. Licence files: LICENSE.

Training data: Not stated for this checkpoint; the M-LSD paper trains on the Wireframe dataset (Huang et al. 2018, no licence stated)..

Licence evidence: https://github.com/lhwcv/mlsd_pytorch/blob/2312205254e66911703decf775f626995d260f17/LICENSE ; https://github.com/lhwcv/mlsd_pytorch/tree/2312205254e66911703decf775f626995d260f17/models

Input size

any H x W >= 32, padded to a multiple of 32 Tested up to (portable, fp16, RTX 5060 Ti 16 GB): mlsd 1080x1920 (0.1 GiB peak allocated, 0.2 reserved)

Speed and memory

Edges, synthetic, 1080x1920

model time (ms): original portable peak memory (MiB, allocated / reserved): original portable
mlsd 35.6 9.33 185 / 212 127 / 170

Startup and first call

model load (s): original portable kernels first call (s): original portable kernels
mlsd 0.21 0.17 – 0.06 0.01 –

torch.compile and TensorRT

model input time: portable compile TensorRT fp16 kernels preparation: compile (cold first call) ONNX + engine build peak MiB (alloc / reserved): portable compile kernels TensorRT (engine + torch)
mlsd 1024x1024 7.65 ms 4.61 ms planned for 0.2.1 – 11.4 s – 72 / 90 101 / 130 – –

Fixed-size cells: time (ms) / peak allocated / peak reserved memory (MiB).

Hardware, protocol and caveats: benchmarks (RTX 5060 Ti 16 GB, sm_120). Original = the original code named above at the precision of portable (fp16, or (fp32) where fp16 is unsupported or not finite); original fp32 = its default fp32 run. Peak memory is the torch allocator's.

Accuracy

Parity with the original code

Every variant is checked against reference outputs of the original code at its pinned commit. CPU, float32: max |diff| <= 0.002 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.02 and p99 <= 0.25 (absolute error of the output edges).

Usage

from fastforks import edges

model = edges.load("mlsd")  # mode="auto": the preferred backend from recorded measurements
result = model("photo.jpg")
result.edges  # [H, W] float32 in [0, 1], 1 = line, input resolution
result.backend  # what ran, e.g. Backend(mode='portable', device='cuda:0', dtype='float16')

Install with pip install fastforks (see https://github.com/kleinicke/fastforks). Other variants: mlsd.

Kernels backend

No kernels backend: a MobileNetV2 CNN (cuDNN); decoding is a few small ops; no custom kernel measured to pay off.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Collection including fastforks/mlsd