ComfyUI_DepthFlow

ComfyUI_DepthFlow
★ 5

深度估计DepthFlowComfyUI_DepthFlow模型自动下载
ComfyUI_DepthFlow 在 ComfyUI 中调用 DepthFlow(Depth-Anything 模型)进行深度估计,自动下载所需模型并生成深度图,便于在工作流中融合深度信息。
💡 自动下载并在工作流中生成深度图以辅助图像合成
🍴 1 Forks💻 Python🔄 2024-09-16
📦
网盘下载
复制链接后前往夸克网盘下载
https://pan.quark.cn/s/e98a62d17551
📄 README

ComfyUI_DepthFlow

comfyui custom node for depthflow

original depthflow website: https://github.com/BrokenSource/DepthFlow

check this for installation: https://brokensrc.dev/get/

For Ubuntu system, I believe run commands below is enough:

sudo apt-get update

sudo apt-get install libegl1-mesa libgl1-mesa-glx libgles2-mesa

apt install libasound2-dev

python -m pip install depthflow

Run the ComfyUI workflow will download depth-anything/Depth-Anything-V2-base-hf from huggingface to your local directory automatically.

you can check it at directory: ~/.cache/huggingface/hub/models–depth-anything–Depth-Anything-V2-base-hf

if OpenGL can find gpu, you will see log like below, and the code will run quite fast, otherwise it will run really slow.

OpenGL Renderer: NVIDIA GeForce RTX …

Good Luck, have fun!