PiDiNet soft edges
PiDiNet (Su et al., ICCV 2021): a small, fast edge detector with pixel-difference convolutions, folded into plain convolutions here; soft edges for the soft-edge ControlNet. Research use only (non-commercial).
experimental Fork of huggingface/controlnet_aux@b1aac31 · backends: portable, kernels
- Paper Pixel Difference Networks for Efficient Edge Detection ICCV 2021 · first released 16 Aug 2021
- Paper Adding Conditional Control to Text-to-Image Diffusion Models ICCV 2023 · first released 10 Feb 2023
Checkpoint pidinet
Paper 2021 Added in 0.2.0
Use it
pip install fastforks Lean install with only what this model needs: pip install "fastforks-core[nc]"
from fastforks import edges
model = edges.load("pidinet") # kernels on a supported GPU, else portable PyTorch
result = model(image)
result.edges
result.backend # what ran: mode, device, dtype, kernels The weights are non-commercial: fastforks downloads them only with FASTFORKS_NONCOMMERCIAL=1 set.
fastforks bench pidinet 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.
| Backend | dtype | Time per call (ms) | vs original fp16 | Peak memory allocated / reserved | Load (s) | First call (s) |
|---|---|---|---|---|---|---|
| Original fp32 | fp32 | not measured | – | – | – | – |
| Original fp16torch.autocast(float16) around the call; huggingface/controlnet_aux@b1aac318b15c pidinet, host OpenCV resize, float post-processing | fp16 | 35.9 | – | 339 MiB/368 MiB | 0.1 | 0.06 |
| Portable fp32 | fp32 | not measured | – | – | – | – |
| Portable | fp16 | 13.1 | 2.7× | 328 MiB/372 MiB | 0.2 | 0.01 |
| Kernels | not measured | – | – | – | – | |
| Portable + torch.compile | not measured here | – | – | – | – | |
| TensorRT | not 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
| Device | Backend | dtype | ms / call | Peak memory | Output vs reference | Input |
|---|---|---|---|---|---|---|
| Apple M1 Pro 16 GB MPS, torch 2.14.1, 2026-11-14 | Original | fp32 | 109 | 1,480 MiB process | – | 1024x1024 |
| Portable | fp16 | 73.2 | 1,349 MiB process | matches | 1024x1024 | |
| Portable | fp32 | 90.8 | 1,359 MiB process | matches | 1024x1024 | |
| Kernels | fp32 | not 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
Non-commercial only
- Code
- LicenseRef-research-only LICENSE
- Weights
- LicenseRef-research-only (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). The file name matches the paper's table 5 BSDS500 model.
- code: LicenseRef-research-only (noncommercial)
- weights: LicenseRef-research-only (assumed from code)
- weights licence not stated by the original authors; assumed to be the code licence
Our reading of the licences, not legal advice.
Weights
table5_pidinet.pth 2.9 MB· hosted on Hugging Facefastforks downloads and checks these files on first use (fastforks download pidinet). Non-commercial weights need FASTFORKS_NONCOMMERCIAL=1.
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 pidinet.
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).
| Check | Tolerance | Measured |
|---|---|---|
| CPU fp32, max |diff| | ≤ 0.002 | not recorded |
| GPU default dtypes, mean |diff| | ≤ 0.02 | 0.00019 |
| GPU default dtypes, p99 |diff| | ≤ 0.25 | 0.00192 |
Recorded for pidinet on RTX 5060 Ti, torch 2.10.0+cu130, 2026-11-17, with these kernels: cv_resample
Details
Soft edge preprocessor of ControlNet 1.1 (controlnet_aux `PidiNetDetector`, ComfyUI's "PiDiNet Soft-Edge Lines"): pixel difference networks (Su et al., ICCV 2021), a 0.7 M-parameter edge detector of difference convolutions, here converted to plain depthwise convolutions (the authors' re-parameterization). Research use only.
- 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 (328 MiB allocated)
- Options
short_side=512>= 64· changes the outputapply_filter=false· changes the outputsafe=false· changes the output
- Outputs
edges- CUDA kernels
cv_resample
- Apple (MPS)
- fp32, fp16
Full reference, generated from the repository
PiDiNet (Su et al., ICCV 2021): a small, fast edge detector with pixel-difference convolutions, folded into plain convolutions here; soft edges for the soft-edge ControlNet. Research use only (non-commercial).
Commercial use: no (code: LicenseRef-research-only (noncommercial); weights: LicenseRef-research-only (assumed from code)).
| variant | input | backend | time (ms) | peak memory (MiB, allocated / reserved) |
|---|---|---|---|---|
pidinet | synthetic (1080x1920) | original portable kernels | 35.9 13.1 – | 339 / 368 328 / 372 – |
pidinet | synthetic (1024x1024) | original portable kernels portable + torch.compile TensorRT fp16 | 18.5 6.59 – 5.66 4.50 | 199 / 236 186 / 228 – 166 / 190 187 / 200 |
Details
- Original code: https://github.com/huggingface/controlnet_aux at
b1aac318b15c - Code licence: LicenseRef-research-only (noncommercial); files:
LICENSE - Weights licence: LicenseRef-research-only (assumed from code)
- Licence evidence: https://github.com/huggingface/controlnet_aux/blob/b1aac318b15c4e65a21bc516dc236ad4bf593d46/src/controlnet_aux/pidi/LICENSE ; https://github.com/hellozhuo/pidinet/blob/master/LICENSE ; https://huggingface.co/lllyasviel/Annotators
- Training data: Not stated for these checkpoints (lllyasviel/Annotators, ControlNet 1.1). The file name matches the paper's table 5 BSDS500 model.
- Options:
short_side= 512 (>= 64; alsoresolution; alsodetect_resolution),apply_filter= False,safe= False - Kernel libraries:
cv_resample - Variants:
pidinet - 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):
pidinet1080x1920 (0.3 GiB peak allocated, 0.4 reserved) pidinet1024x1024, first call: portable + torch.compile 12 s (cold Inductor cache), TensorRT fp16 20 s (ONNX + engine).pidinetoriginal 1080x1920, original 1024x1024: torch.autocast(float16) around the call; huggingface/controlnet_aux@b1aac318b15c pidinet, host OpenCV resize, float post-processingpidinetload / first call: original 0.28 s / 0.058 s, portable 0.16 s / 0.014 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).
| variant | kernels error vs original, mean / p99 | GPU, torch | kernels used |
|---|---|---|---|
pidinet | 0.00019 / 0.00192 | RTX 5060 Ti, torch 2.10.0+cu130 | cv_resample@969307ab22a7:sm_120 |
Example output
No example rendered for this checkpoint yet.