Benign comfyui Download

time-image 1.0.1

Basename is uppercase README.mdModule is one triple-quoted Python literal

Evidence

GitHub service URL reference NOTICE.md · line 0
0# Third-party notices / 第三方声明 Time image bundles third-party code. The root [`LICENSE`](LICENSE) explains how the project's own MIT-licensed code and these upstream licenses fit together; this file is the quick reference. 本仓库包含第三方代码。根目录 [`LICENSE`](LICENSE) 说明了原创代码与第三方许可的关系, 本文件是速查清单。 | Directory / 目录 | Upstream / 上游 | License / 许可 | Key restriction / 关键限制 | | --- | --- | --- | --- | | `custom_controlnet_aux/open_pose/` | [CMU OpenPose](https://github.com/CMU-Perceptual-Computing-Lab/openpose) | CMU OpenPose Software License Agreement — **Academic or non-profit organization nonco
At least four Markdown-style heading lines README.md · lines 1–17
1# Time image
2
3Standalone ComfyUI nodes for image/mask resolution fitting, pose extraction, and depth extraction. The pose backend is bundled locally and does not invoke another node package.
4
5## Nodes
6- **Time・Res Fixer (Img/Mask)** — fit an image and optional mask to a divisible canvas.
7- **Time Pose Extractor** — OpenPose or DWPose, with body, hand, and face switches.
8- **Time Depth Model Loader** and **Time Depth Extractor** — load Depth Anything V2 and generate depth maps.
9
10## Installation
11Copy the `Time-image` folder into `ComfyUI/custom_nodes/` and restart ComfyUI.
12
13## Manual model files
14All models are stored under `ComfyUI/models/Time-image/`, split into `pose/` and `depth/`.
15
16### Pose models
17- From [lllyasviel/ …
imports os __init__.py · lines 1–25
1import math
2
3import numpy as np
4import torch
5import torch.nn.functional as F
6from PIL import Image
7import os
8from contextlib import nullcontext
9
10import comfy.model_management as mm
11from comfy.utils import ProgressBar, load_torch_file
12import folder_paths
13from .depth_anything_v2.dpt import DepthAnythingV2
14import sys
15
16# Keep the detector implementation local to this custom-node package.
17_PACKAGE_DIR = os.path.dirname(os.path.abspath(__file__))
18if _PACKAGE_DIR not in sys.path:
19 sys.path.insert(0, _PACKAGE_DIR)
20
21
⋯4 lines
Python not-in membership check __init__.py · lines 103–108
103:2… raise ValueError(f"Unknown fit mode: {fit}")
104 if method not in _RESAMPLING:
105 raise ValueError(f"Unknown resampling method: {method}")
106
107 batch, orig_h, orig_w, channels = image.shape
108 …
SafeTensors filename suffix literal __init__.py · lines 174–178
174:3… def INPUT_TYPES(cls):
175 return {"required": {"model": (["depth_anything_v2_vits_fp16.safetensors", "depth_anything_v2_vitb_fp16.safetensors", "depth_anything_v2_vitl_fp16.safetensors"], {"default": "depth_anything_v2_vitl_fp16.safetensors"})}}
176
177 RETURN_TYPES = ("TIMEIMAGE_DEPTH_MODEL",)
178 FUNCTION = "load …

Showing the top 5 files — 5 more files (32 regions) not shown.

No evidence locations were recorded for this file. Raw result

Keyboard shortcuts on this page: j for the next sample, k for the previous one, x to go back to the feed, d to download the original bytes, r to re-queue the sample for analysis.