Models · Edges and lines

Line art (informative-drawings)

Informative-drawings line art (MIT CSAIL, CVPR 2022), as packaged for ControlNet: draws the lines of a photo as a sketch-like map, the input of the line-art ControlNet; a fine and a coarse version. MIT code and weights.

experimental Fork of huggingface/controlnet_aux@b1aac31 · backends: portable, kernels

Checkpoint

Paper 2022 Added in 0.2.0

Portable, RTX 5060 Ti 16 GB 18.3 ms 1080x1920, fp16
vs the faster original 1.6× original fp16: 29.8 ms
Peak memory 222 MiB original: 221 MiB
Accuracy vs original fp32 – no test-set run

Use it

pip install fastforks

Lean install with only what this model needs: pip install fastforks-core

from fastforks import edges

model = edges.load("lineart")  # kernels on a supported GPU, else portable PyTorch
result = model(image)
result.edges
result.backend  # what ran: mode, device, dtype, kernels
fastforks bench lineart

Times the model on this machine. load(…, mode="portable") or mode="kernels" picks a backend; usage guide.

Speed and memory

Every backend on one GPU (RTX 5060 Ti 16 GB) and the same input, the authors’ code included. Kernels runs fp16. Portable runs fp16 on CUDA.

BackenddtypeTime per call (ms)vs original fp16Peak memory
allocated / reserved
Load (s)First call (s)
Original fp32fp32not measured ––––
Original fp16torch.autocast(float16) around the call; huggingface/controlnet_aux@b1aac318b15c lineart, host OpenCV resize, float post-processingfp16 29.8–221 MiB/264 MiB0.10.03
Portable fp32fp32not measured ––––
Portablefp16 18.31.6×222 MiB/284 MiB0.20.02
Kernelsnot measured ––––
Portable + torch.compilenot measured here ––––
TensorRTnot measured here ––––

Measured on RTX 5060 Ti 16 GB, torch 2.14.1+cu130, 2026-11-14. First call, 3 warm-up, peak reset, median of 3 rounds x median of 5. Ratios divide two times of this table (same GPU, same input). Original fp16 is the authors’ own precision option, else torch.autocast. torch.compile and TensorRT: build time instead of load time. TensorRT memory (engine, not comparable) is the GPU memory the engine took, read from the driver because TensorRT allocates outside PyTorch, so it can't be compared with the PyTorch peaks of the other rows.

Other devices

DeviceBackenddtypems / callPeak memoryOutput vs referenceInput
Apple M1 Pro 16 GB MPS, torch 2.14.1, 2026-11-14Originalfp32114 1,481 MiB process–1024x1024
Portablefp1666.5 1,362 MiB processmatches1024x1024
Portablefp3295.8 1,361 MiB processmatches1024x1024
Kernelsfp32not implemented–1024x1024

CUDA memory is torch’s peak allocated / reserved; Apple has no such counter, so the Mac rows show the process footprint (weights, Python and torch included). “Output vs reference” compares the device’s output with the stored golden output under the card’s tolerance; – = not checked on that device. Kernels “not implemented” = no kernels for this model on that backend yet: it runs portable there.

Licence and weights

Commercial use allowed

Code
MIT LICENSE
Weights
MIT (assumed from code)(not stated by the authors; assumed to follow the code) source
Training data
Not stated for these checkpoints (lllyasviel/Annotators, ControlNet 1.1); informative-drawings trains on unpaired photographs and line drawings.
  • weights licence not stated by the original authors; assumed to be the code licence

Our reading of the licences, not legal advice.

Weights

sk_model.pth 17.2 MB· hosted on Hugging Face

fastforks downloads and checks these files on first use (fastforks download lineart).

Accuracy

The test set through the authors’ code and through ours: same checkpoint, same protocol. The distance between the original’s fp32 and fp16 runs is what half precision alone costs; our runs should stay within it.

Accuracy not measured for lineart.

Closeness to the original

Beyond the test-set scores: the raw output of ours against the original’s fp32 output on the same input, pixel by pixel. 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).

CheckToleranceMeasured
CPU fp32, max |diff|≤ 0.002 not recorded
GPU default dtypes, mean |diff|≤ 0.02 0.00011
GPU default dtypes, p99 |diff|≤ 0.25 0.00078

Recorded for lineart on RTX 5060 Ti, torch 2.10.0+cu130, 2026-11-17, with these kernels: cudnn_hacccutlass_convigevvol_norm

Details

Line art preprocessor of ControlNet 1.1 (controlnet_aux `LineartDetector`, ComfyUI's "Realistic Lineart"): the informative-drawings generator (Chan, Durand and Isola, CVPR 2022; 3 residual blocks, instance norm) turns a photo into a line drawing. `lineart` is the realistic model, `lineart-coarse` the coarse one.

Input / output
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.
Input size
any H x W >= 32, padded to a multiple of 32; tested up to 1080x1920 (222 MiB allocated)
Options
  • short_side=512>= 64· changes the output
Outputs
edges
CUDA kernels
  • vol_norminstance norm and LeakyReLU on 3D volumes
  • igevIGEV stereo: convolution epilogues, correlation lookups, GRU gates
  • cutlass_convCUTLASS convolutions with the recurrent update (GRU) fused in
  • cudnn_haccconvolutions with fp16 accumulation (cuDNN)
Apple (MPS)
fp32, fp16
Full reference, generated from the repository

Informative-drawings line art (MIT CSAIL, CVPR 2022), as packaged for ControlNet: draws the lines of a photo as a sketch-like map, the input of the line-art ControlNet; a fine and a coarse version. MIT code and weights.

Commercial use: yes.

variantinputbackendtime (ms)peak memory (MiB, allocated / reserved)
lineartsynthetic (1080x1920)original
portable
kernels
29.8
18.3
–
221 / 264
222 / 284
–
lineartsynthetic (1024x1024)original
portable
kernels
portable + torch.compile
TensorRT fp16
15.7
9.93
–
6.49
4.80
141 / 186
129 / 164
–
117 / 164
150 / 176
lineart-coarsesynthetic (1080x1920)original
portable
kernels
30.4
18.3
–
221 / 264
222 / 284
–
lineart-coarsesynthetic (1024x1024)original
portable
kernels
portable + torch.compile
TensorRT fp16
15.8
9.92
–
6.49
4.80
141 / 186
129 / 164
–
117 / 164
150 / 176
Details
  • Original code: https://github.com/huggingface/controlnet_aux at b1aac318b15c
  • Code licence: MIT (permissive); files: LICENSE
  • Weights licence: MIT (assumed from code)
  • Licence evidence: https://github.com/huggingface/controlnet_aux/blob/b1aac318b15c4e65a21bc516dc236ad4bf593d46/src/controlnet_aux/lineart/LICENSE ; https://huggingface.co/lllyasviel/Annotators
  • Training data: Not stated for these checkpoints (lllyasviel/Annotators, ControlNet 1.1); informative-drawings trains on unpaired photographs and line drawings.
  • Options: short_side = 512 (>= 64; also resolution; also detect_resolution)
  • Kernel libraries: vol_norm, igev, cutlass_conv, cudnn_hacc
  • Variants: lineart, lineart-coarse
  • Outputs: edges
  • Input size: any H x W >= 32, padded to a multiple of 32
  • Tested up to (portable, fp16, RTX 5060 Ti 16 GB): lineart 1080x1920 (0.2 GiB peak allocated, 0.3 reserved); lineart-coarse 1080x1920 (0.2 GiB peak allocated, 0.3 reserved)
  • lineart 1024x1024, first call: portable + torch.compile 10 s (cold Inductor cache), TensorRT fp16 10 s (ONNX + engine).
  • lineart-coarse 1024x1024, first call: portable + torch.compile 10 s (cold Inductor cache), TensorRT fp16 10 s (ONNX + engine).
  • lineart original 1080x1920, original 1024x1024: torch.autocast(float16) around the call; huggingface/controlnet_aux@b1aac318b15c lineart, host OpenCV resize, float post-processing
  • lineart-coarse original 1080x1920, original 1024x1024: torch.autocast(float16) around the call; huggingface/controlnet_aux@b1aac318b15c lineart, host OpenCV resize, float post-processing
  • lineart load / first call: original 0.65 s / 0.049 s, portable 0.16 s / 0.019 s
  • lineart-coarse load / first call: original 0.16 s / 0.048 s, portable 0.16 s / 0.019 s
  • Protocol, first call, 3 warm-up, peak reset, median of 3 rounds x median of 5

Parity

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).

variantkernels error vs original, mean / p99GPU, torchkernels used
lineart0.00011 / 0.00078RTX 5060 Ti, torch 2.10.0+cu130cudnn_hacc@cudnn91501, cutlass_conv@988138e042cb:sm_120, igev@f075827d68c6:sm_120, vol_norm@44036d4da567:sm_120
lineart-coarse0.00013 / 0.00103RTX 5060 Ti, torch 2.10.0+cu130cudnn_hacc@cudnn91501, cutlass_conv@988138e042cb:sm_120, igev@f075827d68c6:sm_120, vol_norm@44036d4da567:sm_120

Example output

No example rendered for this checkpoint yet.