coreml-stable-diffusion-3-medium-1024-t5 SD3 Medium T5 — a SD3 community checkpoint on the Sogni Supernet.
No GPU. No setup. Cancel anytime.
SD3 Medium T5 is a SD3 community image model available on the Sogni Supernet — generate credit-free under fair use, no GPU or setup required. Stable Diffusion 3 is a text-to-image base model from Stability AI with improved prompt understanding, better multi-subject composition, stronger typography, and more efficient performance than earlier Stable Diffusion versions. ⚠️ Important Note about the 1024-T5 version: This model needs to run from an external hard drive and requires at least 48 GB of RAM. Running it from your Mac’s internal drive can cause a memory overflow and crash your system. Before installing, make sure Sogni is set to use an external drive by going to Sogni > Settings > Storage in the top menu.
Run it credit-free in the Sogni app, or call it by model id via the API.
SD3 Medium T5 is included on every Sogni plan — generate credit-free under fair use, alongside 100+ other models, from a flat monthly price.
One Sogni API key reaches every model on the Supernet — call SD3 Medium T5 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: 'coreml-stable-diffusion-3-medium-1024-t5',
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 24h # coreml-stable-diffusion-3-medium-1024-t5 is addressable by id via the JavaScript SDK (see the JavaScript tab).
# The REST workflow API routes this family through its flagship alias instead:
curl 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" }
}]
},
"confirm_cost": true
}' Addressable by id via the JavaScript SDK; the REST workflow API routes this family through its flagship alias. Full reference at docs.sogni.ai.
Real generations from Sogni. Hit Use prompt to open the app with SD3 Medium T5 selected and the full prompt preloaded.
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 SD3 Medium T5 by id and pay in Spark.
Runs on a decentralized GPU network where workers share subscription revenue.
SD3 Medium T5 is a SD3 community image model available on the Sogni Supernet — generate credit-free under fair use, no GPU or setup required. Stable Diffusion 3 is a text-to-image base model from Stability AI with improved prompt understanding, better multi-subject composition, stronger typography, and more efficient performance than earlier Stable Diffusion versions. ⚠️ Important Note about the 1024-T5 version: This model needs to run from an external hard drive and requires at least 48 GB of RAM. Running it from your Mac’s internal drive can cause a memory overflow and crash your system. Before installing, make sure Sogni is set to use an external drive by going to Sogni > Settings > Storage in the top menu.
SD3 Medium T5 is unlimited under fair use on a flat monthly Sogni plan — no per-image credits to count.
Create instantly in the Sogni app, or call the Sogni API with model id coreml-stable-diffusion-3-medium-1024-t5.
No. SD3 Medium T5 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.