What exactly does AILab_QwenVL do in this workflow?

AILab_QwenVL runs a Qwen-VL vision-language model on the input from LoadImage. It takes your instruction (prompt) plus the image, then generates text—such as a caption, list of objects, or an answer to a question about the image—which PreviewAny displays.

Do I need an internet connection or API key to run this?

It depends on how AILab_QwenVL is configured in your environment. Many setups load local model weights and run fully offline. If your node is configured to call a remote backend, you may need network access or credentials. Check your node’s model selection and documentation.

How can I control the style and length of the output?

Guide the model with explicit instructions (e.g., "One-sentence caption," "Return keywords separated by commas," or "Output JSON with fields: setting, subjects, actions"). If your node exposes settings like maximum tokens or temperature, use them to limit length and make results more deterministic.

How do I get more accurate results (especially for text in images)?

Use clear, specific prompts (e.g., "Transcribe all legible text exactly, line by line"), provide sufficiently large, sharp images, and reduce temperature for factual tasks. If the scene is busy, crop to the relevant area before running LoadImage so the model focuses on what matters.

AI on the Lot 2026 - QwenVL - i2t

此工作流在 ComfyUI 中使用 Qwen-VL 将任意图像转换为可按指令生成的描述文本。它是一条简单且稳定的链路：LoadImage 将源帧或照片加载进画面，AILab_QwenVL 运行 Qwen-VL 视觉语言模型，根据你的指令生成描述或回答，PreviewAny 则直接在 UI 中显示生成文本。由于 AILab_QwenVL 同时接收图像与提示词输入，你可以把输出引导为简短的 alt 文本、详细的场景拆解、标签，甚至 OCR 风格的转写。

从技术角度看，AILab_QwenVL 会编码视觉内容，并在你的指令条件下解码生成文本（例如“用一句话描述这个场景”或“列出物体并给出数量”）。你通常可以调整生成行为（例如 temperature 或最大输出长度，取决于你的节点构建是否暴露这些选项），在创意与精确之间取得平衡。最小化的节点画面让它运行更快、也更适合教学；用于生成一致的图像描述、制作记录或元数据时无需额外的后处理节点。PreviewAny 会渲染字符串输出，便于你直接从 ComfyUI 复制。

API

通过代码使用此工作流

每个 Comfy 工作流都是一个 JSON 图。下面的内容就是此工作流的完整数据，ComfyUI 运行时也是如此——你可以从该 URL 获取、放入版本控制，或在 ComfyUI 中加载并逐节点运行。

231992fee1a6.json

正在获取工作流 JSON…

使用 Comfy SDK 从 TypeScript 或 Python 运行。相同代码可用于 Comfy Cloud 或你自托管的 ComfyUI——只需更改基础 URL。

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

// Run this workflow (TypeScript)
import { Comfy } from "@comfyorg/sdk";

const client = new Comfy({ apiKey: "comfyui-..." });
const wf = await client.workflows.fromFile("workflow_api.json");
const job = await client.run(wf);
await job.getOutputs("<output-node-id>")[0].toFile("output.png");

SDK 需要 API 格式的工作流：在 ComfyUI 中打开此工作流，使用文件 → 导出工作流（API）。

Comfy Cloud API 访问需要包含 API 密钥的套餐。

SDK 文档获取 API 密钥

常见问题