Stable Diffusion 3.5 Large is a text-to-image model creating high-res, detailed images in varied styles via Query-Key Normalization. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle

$0.06per run·~16 / $1

An astronaut in a sleek, white and orange spacesuit stands on the ridge of a crater on an alien planet, looking out at a swirling nebula of purple and green in the sky. The planet's surface is made of dark, crystalline rock that faintly glimmers. The astronaut's helmet reflects the alien landscape. High-detail science fiction illustration, epic scale, sense of wonder and solitude. --ar 16:9

Iceland's black sand beach on the south coast, early morning mist lingers, immense basalt columns stand solemnly in the sea. A few puffins are perched on the rocks. The sky is a soft gradient of pink and light blue, with gentle waves lapping the black sand. Minimalist composition, ethereal and serene, capturing the raw beauty of nature. Long exposure photography, making the water's surface smooth as silk. --ar 21:9

Aerial view of a futuristic Tokyo on a rainy night. Towering holographic billboards and skyscrapers intertwine, neon lights reflecting on the wet streets, creating cyberpunk blue, purple, and pink glows. Flying shuttles and drones streak between buildings, leaving long light trails. Extremely detailed, high-tech, dystopian atmosphere. Wide-angle lens, ultra-high definition, 8K resolution. --ar 16:9

A giant, antique gramophone stands in the middle of a vast, cracked desert under a sky with two moons. Instead of sound, a flock of monarch butterflies emerges from its large brass horn, flying towards the horizon. The scene is surreal and symbolic, with a color palette of desert ochre and deep twilight blue, sharp shadows cast by the low moons. In the style of Salvador Dalí. --ar 3:2 --s 800

A giant, antique gramophone stands in the middle of a vast, cracked desert under a sky with two moons. Instead of sound, a flock of monarch butterflies emerges from its large brass horn, flying towards the horizon. The scene is surreal and symbolic, with a color palette of desert ochre and deep twilight blue, sharp shadows cast by the low moons. In the style of Salvador Dalí. --ar 3:2 --s 800

A cozy, cluttered artist's studio on a sunny afternoon. Canvases lean against the walls, brushes are scattered in jars, and spots of paint dot the wooden floor. A ginger cat is sleeping curled up on a worn-out armchair near a large window. Warm, golden sunlight streams in, illuminating dust particles in the air. Realistic, warm, and inviting atmosphere, shot on a 50mm lens. --ar 5:4

On a rustic wooden dining table, a freshly baked apple pie rests, its crust golden and crisp, with steaming cinnamon apple filling peeking through the lattice gaps. Beside it sits a small bowl of vanilla ice cream, just beginning to melt. Afternoon sunlight slants through a window, creating warm light spots, the air filled with the sweet aroma of butter and sugar. Macro shot, very shallow depth of field, incredibly appetizing food details, full of cozy, homemade warmth. --ar 4:3 --s 700

A seven-spotted ladybug resting on a green leaf covered with crystal-clear water droplets after a rain. The droplets act like magnifying glasses, clearly reflecting the surrounding environment. The ladybug's carapace shines with a vibrant red gloss in the sunlight. Extreme macro photography, ultra-sharp details showing the fine hairs on the ladybug and the surface tension of the water droplets. Soft green bokeh background, fresh, natural, and full of life. --ar 3:2 --style raw
Stable Diffusion 3.5 Large is Stability AI's flagship text-to-image and image-to-image generation model that creates stunning, highly detailed images from text descriptions. With advanced prompt understanding and flexible aspect ratios, it delivers exceptional quality for creative and professional projects.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the image you want to generate. |
| image | No | Source image for image-to-image transformation. |
| aspect_ratio | No | Output aspect ratio: 1:1, 3:4, 4:3, 16:9, 9:16 (default: 1:1). |
| seed | No | Set for reproducibility; -1 for random. |
| Aspect Ratio | Best For |
|---|---|
| 1:1 | Instagram posts, profile pictures, icons |
| 3:4 | Portrait photos, Pinterest |
| 4:3 | Classic format, presentations |
| 16:9 | YouTube thumbnails, widescreen displays |
| 9:16 | TikTok, Instagram Stories, mobile content |
Text-to-Image:
Image-to-Image:
| Output | Price |
|---|---|
| Per image | $0.06 |
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/stability-ai/stable-diffusion-3.5-large with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Stable Diffusion 3.5 Large below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "1:1",
"seed": -1
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/stability-ai/stable-diffusion-3.5-large" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/stability-ai/stable-diffusion-3.5-large";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "1:1",
"seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "1:1",
"seed": -1
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/stability-ai/stable-diffusion-3.5-large", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout"}:
raise RuntimeError(result)
if status not in {"created", "processing"}:
raise RuntimeError(f"Unexpected status: {status}")
time.sleep(2)Stable Diffusion 3.5 Large is a Stability AI model for image generation, exposed as a REST API on WaveSpeedAI. Stable Diffusion 3.5 Large is a text-to-image model creating high-res, detailed images in varied styles via Query-Key Normalization. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/stability-ai/stability-ai-stable-diffusion-3.5-large.
Stable Diffusion 3.5 Large starts at $0.060 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
Key inputs: `prompt`, `image`, `aspect_ratio`, `seed`, `enable_base64_output`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/stability-ai/stability-ai-stable-diffusion-3.5-large.
Median end-to-end generation time on WaveSpeedAI is around 1 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (Stability AI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.