Stable Diffusion 3.5 Medium is a 2.5B-parameter text-to-image model with the improved MMDiT-X architecture for quality images. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle

$0.035per run·~28 / $1

An elaborate Steampunk-style "Merlion" airship hovers over a Victorian-era Boat Quay. The airship's body is constructed from brass, mahogany, and a complex network of gears and pipes, billowing steam. Below, people in 19th-century gowns and top hats look up in amazement. The scene is filled with retro-futuristic details and imagination. --ar 16:9

A tumultuous ocean violently crashing against black reefs as a storm approaches. The sky is filled with dark, heavy clouds, and a bolt of lightning tears across the sky, illuminating the churning waves. The painting is full of dramatic power and emotion, in the style of J.M.W. Turner, emphasizing the sublime and awesome power of nature. The oil paint texture is heavy, and the colors are deep and moody.

An afternoon scene at the Singapore River, by Boat Quay, with its shophouses and crowds. Painted in an Impressionist style, mimicking the brushwork of Monet, with a focus on capturing light. Short, thick brushstrokes and bright colors, with the reflection of the sun creating sparkling spots on the water's surface. The image is vibrant and slightly blurred, evoking a cheerful and lively atmosphere. --ar 16:9

A serene and magnificent tropical rainforest landscape, with mist-shrouded mountains in the distance. A waterfall cascades from a high cliff into a clear stream. Sunlight filters through the dense canopy, casting a soft glow. The style is detailed and realistic, filled with an idealized and reverent depiction of nature, possessing the epic scale and tranquil atmosphere of the Hudson River School. --ar 16:9

On a wooden table covered with a dark velvet cloth, there is a silver platter filled with tropical fruits (rambutans, mangosteens, mangoes), a parrot, and an exquisite glass goblet. The lighting is soft, and the details are rendered with extreme realism, showcasing the texture and reflection of each object. Possesses the intricate detail and symbolic meaning of the 17th-century Flemish school.

Singapore's Gardens by the Bay depicted in the style of a Japanese Ukiyo-e woodblock print. The giant Supertrees are drawn like traditional pine trees from classic prints, with simple yet powerful lines. The background features a flat, graded sky and stylized clouds. A couple in modern, modified kimonos strolls across a bridge. The image blends traditional art with a modern landmark, mimicking the style of Katsushika Hokusai.
Generate stunning images from text prompts with Stability AI's Stable Diffusion 3.5 Medium. This versatile model delivers high-quality results for both text-to-image and image-to-image generation, with excellent prompt adherence and artistic flexibility.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the image you want to generate. |
| image | No | Optional reference image for image-to-image generation (upload or URL). |
| aspect_ratio | No | Output aspect ratio (e.g., 16:9, 1:1, 9:16). Default: 16:9. |
| seed | No | Random seed for reproducibility. Use -1 for random. |
| enable_base64_output | No | API only: Returns base64 string instead of URL. |
Flat rate per image generation.
| Output | Cost |
|---|---|
| Per image | $0.035 |
| Images Generated | Total Cost |
|---|---|
| 1 | $0.035 |
| 10 | $0.35 |
| 30 | $1.05 |
| 100 | $3.50 |
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/stability-ai/stable-diffusion-3.5-medium with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Stable Diffusion 3.5 Medium below.
set -euo pipefail
: "${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-medium" \
-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-medium";
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-medium", 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 Medium is a Stability AI model for image generation, exposed as a REST API on WaveSpeedAI. Stable Diffusion 3.5 Medium is a 2.5B-parameter text-to-image model with the improved MMDiT-X architecture for quality images. 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-medium.
Stable Diffusion 3.5 Medium starts at $0.035 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-medium.
Median end-to-end generation time on WaveSpeedAI is around 8 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.