Krea-2: Metinden Görsele

This workflow turns text prompts into images using Krea-2 Turbo, a distilled text-to-image model designed for speed and expressive, stylized results. It includes a ResolutionSelector so you can switch aspect ratios without touching width/height by hand, optional style LoRAs for creative control, and a SaveImage node that writes finished renders to your ComfyUI/output folder. A MarkdownNote in the graph links to the official Krea-2 model and LoRA resources so you can install the exact files the graph expects.

Technically, your prompt flows into the Krea‑2 Turbo inference node (b0e5ca93-2731-42b9-8e0a-d28ea851ff81), which loads a diffusion checkpoint such as krea2_turbo_fp8_scaled.safetensors. If you select one or more LoRAs from ComfyUI/models/loras, those adapters are applied during sampling to steer style. The ResolutionSelector subgraph outputs a matched width/height pair to the Krea‑2 node so you can generate at common sizes reliably. The image tensor then routes to SaveImage, which saves numbered files and embeds metadata for reproducibility. The graph is grouped into a compact subgraph so you can work from a single control surface instead of hunting through nodes.

It’s especially useful for concept art and visual brainstorming: start with a general idea, toggle a style LoRA to explore different looks, iterate seeds, and lock a resolution preset for downstream design work. For best control, include any LoRA trigger words in your prompt and start with a moderate LoRA weight (around 0.6), then fine‑tune from there. See the linked Krea‑2 and LoRA docs for model variants and style lists.

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.

11657ed32877.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 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");

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.

SSS

Sık Sorulan Sorular

Tüm iş akışlarını gör
Character
Cinematic
Image to Video
Lip Sync
Multiple Angles
Portrait
Style Reference
Style Transfer
Text to Video
Video Generation
Video
Showing 30 of 30 templates