Lotus Depth - After
Lotus Depth - Before

The 'Lotus Depth' workflow in ComfyUI is designed for efficient monocular depth estimation, providing high-detail retention in image processing tasks. This workflow leverages the Stability model, specifically SD1.5, to perform zero-shot depth estimation, meaning it does not require any prior training on specific datasets. The process begins by loading an image using the LoadImage node, after which the image is processed through a series of nodes that include a custom node identified by c7d32155-757f-4e5d-a139-7e438da96f2f. This node is crucial for executing the depth estimation algorithm. The final output is saved using the SaveImage node, ensuring that the detailed depth information is preserved effectively.

This workflow is particularly useful for applications that require high fidelity in depth perception from single images, such as virtual reality environments or advanced 3D modeling. By utilizing the power of the Stability model, the workflow maintains a balance between computational efficiency and output quality, making it an excellent choice for developers and artists alike who need reliable depth maps without extensive computational resources.

API

Use this workflow from code

Every Comfy workflow is a JSON graph. The payload below is this workflow, exactly as ComfyUI runs it — fetch it from the URL, keep it in version control, or load it in ComfyUI and run it node by node.

image_lotus_depth_v1_1.json
Fetching workflow JSON…

Run it from TypeScript or Python with the Comfy SDK. The same code targets Comfy Cloud or a ComfyUI you host yourself — only the base URL changes.

// Install (beta)
npm i @comfyorg/sdk

// Run "Lotus Depth" (TypeScript)
import { Comfy } from "@comfyorg/sdk";

const client = new Comfy({ apiKey: "comfyui-..." });

// This workflow, exported in API format (see note below)
const wf = await client.workflows.fromFile("image_lotus_depth_v1_1_api.json");

const asset = client.assets.fromFile("input.png");
wf.setInput("12", "image", asset); // LoadImage

const job = await client.run(wf);
await job.getOutputs("9")[0].toFile("output.png"); // SaveImage

The SDK takes a workflow in API format: open this workflow in ComfyUI and use File → Export Workflow (API).

Comfy Cloud API access requires a plan with an API key.

FAQ

Frequently Asked Questions

View all workflows
Showing 30 of 30 templates