The Qwen-Image 2512 Turbo workflow is designed for rapid image generation using a streamlined process that leverages the Qwen-Image 2512 model. This workflow is particularly useful for users who need quick visual outputs from text prompts, albeit with a slight compromise on image quality to achieve faster results. The workflow integrates several key nodes, such as the VAELoader, CLIPLoader, and UNETLoader, which are essential for loading and processing the model components. The KSampler node plays a crucial role in generating latent images, while the LoraLoaderModelOnly node is used to apply LoRA (Low-Rank Adaptation) techniques to enhance the model's efficiency.
This workflow operates in three main steps: loading the necessary models, setting the image size, and processing the text prompt. The ModelSamplingAuraFlow node is crucial for sampling and refining the image output, ensuring that the final result aligns with the user's prompt. By utilizing the CLIPTextEncode node, the workflow effectively translates text prompts into visual concepts, which are then decoded into images using the VAEDecode node. The ConditioningZeroOut node helps in managing the conditioning process, ensuring that the image generation remains consistent and aligned with the input parameters. This workflow is ideal for scenarios where speed is prioritized over high fidelity, making it a practical choice for rapid prototyping and concept visualization.
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.
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 "Qwen-Image 2512 Turbo" (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_qwen_image_2512_with_2steps_lora_api.json");
wf.setInput("108", "text", "your prompt here"); // CLIPTextEncode
const job = await client.run(wf);
await job.getOutputs("123")[0].toFile("output.png"); // SaveImageThe 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.
常見問題
