The NewBie Exp0.1 workflow introduces a groundbreaking approach to anime-style image generation through its innovative Next-DiT architecture. This new model, developed by NewBieAI Lab, leverages structured XML prompts to enhance the generation of multi-character scenes and precise attribute control. By incorporating XML, users can define complex scenes with multiple characters, each with distinct attributes, without losing coherence or detail. This advancement marks a significant leap from traditional text-to-image models, which often struggle with maintaining clarity and detail in complex scenes.
What sets NewBie Exp0.1 apart is its ability to seamlessly integrate detailed prompt structures with cutting-edge image synthesis. The Next-DiT architecture is designed to interpret structured data more effectively, resulting in images that are not only visually appealing but also rich in narrative depth. This makes it an invaluable tool for creators looking to push the boundaries of anime art, offering unprecedented control over the creative process while ensuring high-quality output.
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 "NewBie Exp0.1：動漫產生" (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_newbieimage_exp0_1-t2i_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
