At 2.5 billion parameters, with improved MMDiT-X architecture and training methods, this model is designed to run “out of the box” on consumer hardware, striking a balance between quality and ease of customization. It is capable of generating images ranging between 0.25 and 2 megapixel resolution.
At 2.5 billion parameters, with improved MMDiT-X architecture and training methods, this model is designed to run “out of the box” on consumer hardware, striking a balance between quality and ease of customization. It is capable of generating images ranging between 0.25 and 2 megapixel resolution.
You can use cURL or any other http client to run inferences:
curl -X POST \
-d '{"prompt": "A photo of an astronaut riding a horse on Mars."}' \
-H "Authorization: bearer $DEEPINFRA_TOKEN" \
-H 'Content-Type: application/json' \
'https://api.deepinfra.com/v1/inference/stabilityai/sd3.5-medium'
which will give you back something similar to:
{
"images": [
"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAIAAACQd1PeAAAADElEQVQI12PQz3wAAAJDAXkkWn+MAAAAAElFTkSuQmCC"
],
"nsfw_content_detected": [
false
],
"seed": 42,
"request_id": null,
"inference_status": {
"status": "unknown",
"runtime_ms": 0,
"cost": 0.0,
"tokens_generated": 0,
"tokens_input": 0
}
}
num_inference_steps
integernumber of denoising steps
Default value: 35
Range: 1 ≤ num_inference_steps ≤ 50
aspect_ratio
stringindirectly defines the width and height
Default value: "1:1"
Allowed values: 1:1
16:9
21:9
3:2
2:3
4:5
5:4
9:16
9:21
guidance_scale
numberclassifier-free guidance, higher means follow prompt more closely
Default value: 7
Range: 0 ≤ guidance_scale ≤ 20
webhook
fileThe webhook to call when inference is done, by default you will get the output in the response of your inference request