The LongCat Image: Text to Image workflow in ComfyUI is designed to transform textual descriptions into photorealistic images. By leveraging the LongCat model, this workflow can interpret both English and Chinese text prompts to generate visually accurate and detailed images. The process begins with the '4cdb8c8f-7b15-4921-a2b1-383d5c2d9105' node, which is responsible for interpreting the text input and converting it into a format suitable for image generation. The 'ResolutionSelector' node allows users to specify the desired output resolution, ensuring flexibility in the final image quality. The 'SaveImage' node then captures and stores the generated image, completing the workflow.
This workflow is particularly useful for users who need to create images based on specific textual descriptions, such as content creators, marketers, or educators. The integration of the LongCat model ensures that the generated images are not only photorealistic but also accurately reflect the nuances of the input text. Additionally, the workflow's support for both English and Chinese text makes it versatile for a wide range of applications. The use of subgraphs within ComfyUI enhances the modularity and efficiency of this workflow, allowing for easy customization and scalability.
API
從程式碼使用此工作流
每個 Comfy 工作流都是一個 JSON 圖。下方的 payload 就是此工作流，與 ComfyUI 執行時完全相同 — 你可以從此 URL 取得、放入版本控制，或在 ComfyUI 載入並逐節點執行。
使用 Comfy SDK 以 TypeScript 或 Python 執行。相同程式碼可用於 Comfy Cloud 或你自架的 ComfyUI — 只需更改 base URL。
// Install (beta)
npm i @comfyorg/sdk
// Run "LongCat圖像：文生圖" (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_longcat_text_to_image_api.json");
const job = await client.run(wf);
await job.getOutputs("9")[0].toFile("output.png"); // SaveImageSDK 需使用 API 格式的工作流：請在 ComfyUI 開啟此工作流，並使用 檔案 → 匯出工作流（API）。
常見問題
