Text → image · Image editing · Reference images
ImagePopular
FLUX.2 [dev]
flux2_dev_fp8 Black Forest Labs’ flagship — top-tier fidelity with up to six reference images.
No GPU. No setup. Cancel anytime.
![Sample output from FLUX.2 [dev]](/models/samples/flux-2-dev.jpg)
flux2_dev_fp8 Black Forest Labs’ flagship — top-tier fidelity with up to six reference images.
No GPU. No setup. Cancel anytime.
FLUX.2 [dev] is the highest-fidelity open-weights image model on the Supernet. It excels at photorealism, complex composition, and prompt adherence, and accepts up to six reference images for guided generation and editing in one pass.
It is the default model for the REST workflow API’s generate_image tool. Budget roughly two minutes per full-quality render; drop the step count for faster drafts.
On the Sogni API you pay per render in Spark (1 Spark = $0.005). Prefer a flat rate? The Sogni app runs FLUX.2 [dev] and 100+ other models credit-free under fair use.
| Configuration | Spark | USD |
|---|---|---|
| 1024 × 1024 · 20 steps | 4.15 Spark | $0.021 |
| 1024 × 1024 · 28 steps | 5.80 Spark | $0.029 |
One Sogni API key reaches every model on the Supernet — call FLUX.2 [dev] by id.
import { SogniClient } from '@sogni-ai/sogni-client';
const client = await SogniClient.createInstance({
appId: crypto.randomUUID(),
apiKey: process.env.SOGNI_API_KEY,
network: 'fast',
});
const project = await client.projects.create({
type: 'image',
modelId: 'flux2_dev_fp8',
positivePrompt: 'a slothicorn surfing a wave of liquid paint, studio lighting',
numberOfMedia: 1,
});
const [url] = await project.waitForCompletion();
console.log(url); // result link — download within 24hcurl https://api.sogni.ai/v1/creative-agent/workflows \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $SOGNI_API_KEY" \
-d '{
"input": {
"title": "First render",
"steps": [{
"id": "step1",
"toolName": "generate_image",
"arguments": { "prompt": "a slothicorn surfing a wave of liquid paint, studio lighting", "model": "flux2" }
}]
},
"confirm_cost": true
}' REST workflow alias: flux2. Pin the exact id with the SDK. Full reference at docs.sogni.ai.
Most platforms ration credits or rent a cloud GPU by the hour. Sogni gives you a flat monthly price for credit-free fair-use generation, powered by a creator-owned GPU network — or per-render Spark pricing if you'd rather pay as you go via the API.
One flat price in the app. Generate under fair use without a per-image meter.
Image, video, music, and language models in one workspace and one API key.
Prefer pay-as-you-go? Call FLUX.2 [dev] by id and pay in Spark.
Runs on a decentralized GPU network where workers share subscription revenue.
![Sample from FLUX.1 [schnell]](/models/samples/flux-1-schnell.jpg)
ImageFast FLUX.1 [schnell] The speed classic — four-step FLUX for instant iteration. from 0.80 Spark · $0.004 
Image Z-Image The full-step sibling of Turbo — same model line, maximum detail. from 4.00 Spark · $0.02 
Image Qwen Image Edit 2511 The strongest preservation editor — same face, same scene, new instruction. from 4.15 Spark · $0.021 FLUX.2 [dev] is the highest-fidelity open-weights image model on the Supernet. It excels at photorealism, complex composition, and prompt adherence, and accepts up to six reference images for guided generation and editing in one pass.
From 4.15 Spark ($0.021) per render on the Sogni API (1 Spark = $0.005) — or unlimited under fair use on a flat monthly Sogni plan.
Create instantly in the Sogni app, or call the Sogni API with model id flux2_dev_fp8.
No. FLUX.2 [dev] runs on the Sogni Supernet — a decentralized network of creator GPUs — with no local install or graphics card required.
Create in the app, or build with the API. Your call.