pidinet / README.md
Flor's picture
card: update from fastforks 1cbf1671
c4e6f55 verified
|
Raw History Blame Contribute Delete
5.26 kB
metadata
library_name: fastforks
pipeline_tag: image-to-image
license: other
license_name: see-model-card
license_link: >-
  https://github.com/huggingface/controlnet_aux/blob/b1aac318b15c4e65a21bc516dc236ad4bf593d46/src/controlnet_aux/pidi/LICENSE
tags:
  - edges
  - edge-detection
  - line-art
  - controlnet-preprocessor
  - cuda
  - pytorch
  - fastforks
  - fastforks-card

PiDiNet soft edges (fastforks)

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.

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.

Author weight repos: https://huggingface.co/lllyasviel/Annotators.

Task: edges. Tier: experimental. Outputs: edges. 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
pidinet@1 table5_pidinet.pth 80860ac26725 LicenseRef-research-only (assumed from code) no

Licence

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

Code licence: LicenseRef-research-only; the authors do not state a separate weights licence.

Training data: Not stated for these checkpoints (lllyasviel/Annotators, ControlNet 1.1). The file name matches the paper's table 5 BSDS500 model..

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

Input size

any H x W >= 32, padded to a multiple of 32 Tested up to (portable, fp16, RTX 5060 Ti 16 GB): pidinet 1080x1920 (0.3 GiB peak allocated, 0.4 reserved)

Speed and memory

Edges, synthetic, 1080x1920

model time (ms): original portable peak memory (MiB, allocated / reserved): original portable
pidinet 35.9 13.1 339 / 368 328 / 372

Startup and first call

model load (s): original portable kernels first call (s): original portable kernels
pidinet 0.28 0.16 – 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)
pidinet 1024x1024 6.59 ms 5.66 ms 4.50 ms – 12.4 s 20.4 s 186 / 228 166 / 190 – 187 / 200

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

# non-commercial weights: run with FASTFORKS_NONCOMMERCIAL=1 in the environment
model = edges.load("pidinet")  # 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: pidinet.

Kernels backend

No kernels backend: the converted network is plain convolutions (cuDNN); no custom kernel measured to pay off.