Stable Diffusion 3.5 Large API

stability-ai/stable-diffusion-v3.5-large

Güçlü prompt uyumu, doğru tipografi ve çeşitli görsel stillerle metin prompt’undan yüksek kaliteli görseller üretin.

görsel megapikseli başına 0.065

OpenAPI

Input

Prompt

The text prompt describing the image to generate.

Image Size

Width

Height

The size of the generated image. Choose a preset (e.g. 'square_hd', 'portrait_16_9') or pass a custom {width, height} object.

Num Inference Steps

Min: 1 - Max: 50

The number of inference steps to perform. More steps can improve detail at the cost of speed.

Additional Settings

Customize your input with more control.

Guidance Scale

Min: 0 - Max: 20

The CFG (Classifier Free Guidance) scale. Higher values increase adherence to the prompt.

Negative Prompt

Describe what you do NOT want to appear in the image.

Seed

The same seed and the same prompt given to the same version of the model will output the same image every time.

Output Format

The format of the generated image.

Enable Safety Checker

Safety checker can only be disabled on API call

ControlNet

Path

URL or HuggingFace path to the ControlNet model.

End Percentage

Min: 0 - Max: 1

Fraction of the denoising process at which ControlNet conditioning ends.

Start Percentage

Min: 0 - Max: 1

Fraction of the denoising process at which ControlNet conditioning starts.

Control Image URL

URL of the control image that guides the generation.

Conditioning Scale

Min: 0 - Max: 2

How strongly the ControlNet conditioning is applied.

Optional ControlNet conditioning. Provide a control model path and a control image to guide structure/composition.

LoRAs

Optional list of LoRA weights to apply. Each entry references a LoRA path and an optional scale.

IP-Adapter

Path

URL or HuggingFace path to the IP-Adapter weights.

Scale

How strongly the IP-Adapter conditioning is applied.

Image URL

URL of the reference image used for IP-Adapter conditioning.

Subfolder

Optional subfolder within the IP-Adapter repository.

Weight Name

Optional specific weight file name within the IP-Adapter repository.

Mask Image URL

Optional URL of a mask image restricting where IP-Adapter conditioning applies.

Mask Threshold

Min: 0.01 - Max: 0.99

Threshold used to binarize the IP-Adapter mask.

Image Encoder Path

URL or HuggingFace path to the image encoder.

Image Encoder Subfolder

Optional subfolder within the image encoder repository.

Image Encoder Weight Name

Optional specific weight file name within the image encoder repository.

Optional IP-Adapter image prompting. Provide an adapter path and a reference image to condition generation on that image.

You need to be logged in to run this model and view results.

Output

{
  "error": "",
  "inferenceTime": 4544,
  "output": [
    "https://media.modelrunner.ai/BoL6SdOWAl9Dk1sZcm0H4.jpeg"
  ],
  "input": {
    "loras": [],
    "prompt": "a bold retro travel poster of the Swiss Alps at sunset, clean flat vector shapes, geometric mountains, muted terracotta and sage palette, vintage typography reading 'Explore'",
    "image_size": "portrait_4_3",
    "output_format": "jpeg",
    "guidance_scale": 5,
    "negative_prompt": "",
    "num_inference_steps": 28,
    "enable_safety_checker": true
  },
  "logs": "Generated 1 output(s)"
}

Generated in 4.544 seconds

Logs (1 lines)

Örnekler

Stable Diffusion 3.5 Large API

Stable Diffusion 3.5 Large is a text-to-image AI model by stability-ai. On ModelRunner it runs through a REST API or via MCP from any AI assistant, at $0.065 per megapixel.

POST https://queue.modelrunner.run/stability-ai/stable-diffusion-v3.5-large

cURL

# Submit a request to the queue. Input fields go at the top level of the
# body. The optional reserved "metadata" object holds your own flat string
# tags — stored on the request, never sent to the model; filter later with
# GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>.
curl -X POST https://queue.modelrunner.run/stability-ai/stable-diffusion-v3.5-large \
  -H "Authorization: Key $MRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "loras": [],
    "prompt": "a bold retro travel poster of the Swiss Alps at sunset, clean flat vector shapes, geometric mountains, muted terracot…",
    "image_size": "portrait_4_3",
    "output_format": "jpeg",
    "guidance_scale": 5,
    "negative_prompt": "",
    "num_inference_steps": 28,
    "enable_safety_checker": true,
    "metadata": {
      "project": "my-project"
    }
  }'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }

# Poll status_url until "COMPLETED", then fetch the result
curl "https://queue.modelrunner.run/stability-ai/stable-diffusion-v3.5-large/requests/$REQUEST_ID/status" \
  -H "Authorization: Key $MRUN_API_KEY"
curl "https://queue.modelrunner.run/stability-ai/stable-diffusion-v3.5-large/requests/$REQUEST_ID" \
  -H "Authorization: Key $MRUN_API_KEY"

JavaScript

import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("stability-ai/stable-diffusion-v3.5-large", {
  input: {
    "loras": [],
    "prompt": "a bold retro travel poster of the Swiss Alps at sunset, clean flat vector shapes, geometric mountains, muted terracot…",
    "image_size": "portrait_4_3",
    "output_format": "jpeg",
    "guidance_scale": 5,
    "negative_prompt": "",
    "num_inference_steps": 28,
    "enable_safety_checker": true
  },
});
console.log(result);

Python

import os
import requests

headers = {"Authorization": f"Key {os.environ['MRUN_API_KEY']}"}

submitted = requests.post(
    "https://queue.modelrunner.run/stability-ai/stable-diffusion-v3.5-large",
    headers=headers,
    json={
      "loras": [],
      "prompt": "a bold retro travel poster of the Swiss Alps at sunset, clean flat vector shapes, geometric mountains, muted terracot…",
      "image_size": "portrait_4_3",
      "output_format": "jpeg",
      "guidance_scale": 5,
      "negative_prompt": "",
      "num_inference_steps": 28,
      "enable_safety_checker": true
    },
).json()

# Poll submitted["status_url"] until "COMPLETED", then:
result = requests.get(submitted["response_url"], headers=headers).json()

Input parameters

Input parameters of Stable Diffusion 3.5 Large
Name	Type	Required	Description
prompt	string	yes	The text prompt describing the image to generate.
image_size	enum	no	The size of the generated image. Choose a preset (e.g. 'square_hd', 'portrait_16_9') or pass a custom {width, height} object. One of: `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9`. Default: "landscape_4_3".
num_inference_steps	integer	no	The number of inference steps to perform. More steps can improve detail at the cost of speed. Default: 28.
guidance_scale	number	no	The CFG (Classifier Free Guidance) scale. Higher values increase adherence to the prompt. Default: 3.5.
negative_prompt	string	no	Describe what you do NOT want to appear in the image. Default: "".
seed	integer	no	The same seed and the same prompt given to the same version of the model will output the same image every time.
output_format	enum	no	The format of the generated image. One of: `jpeg`, `png`. Default: "jpeg".
enable_safety_checker	boolean	no	If set to true, the safety checker will be enabled. Default: true.
controlnet	object	no	Optional ControlNet conditioning. Provide a control model path and a control image to guide structure/composition.
loras	array	no	Optional list of LoRA weights to apply. Each entry references a LoRA path and an optional scale. Default: [].
ip_adapter	object	no	Optional IP-Adapter image prompting. Provide an adapter path and a reference image to condition generation on that image.

Machine-readable: OpenAPI schema · llms.txt

Use Stable Diffusion 3.5 Large from Claude & Cursor (MCP)

Point Claude Code, Claude Desktop, Cursor, or any MCP client at the ModelRunner MCP server and Stable Diffusion 3.5 Large becomes a tool your assistant can call directly — it authorizes via OAuth (no API key in config) and runs this model with the run_model tool using the endpoint stability-ai/stable-diffusion-v3.5-large.

MCP client config (Claude Desktop, Cursor)

{
  "mcpServers": {
    "modelrunner": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.modelrunner.run/mcp"]
    }
  }
}

Claude Code

claude mcp add --transport http modelrunner https://mcp.modelrunner.run/mcp

Then ask your assistant, for example: “Run stability-ai/stable-diffusion-v3.5-large on ModelRunner to generate image”. MCP setup guide.

Model Detayları

Stable Diffusion 3.5 Large, bir metin prompt’unu yüksek kaliteli bir görsele dönüştürür. Stability AI’ın 8 milyar parametreli amiral gemisi Multimodal Diffusion Transformer (MMDiT) modelidir; güçlü prompt uyumu, doğru tipografi ve fotogerçekçilikten illüstrasyona ve 3D render’lara uzanan geniş bir stil yelpazesi için geliştirilmiştir. Betimleyici bir prompt verin ve bir görsel boyutu seçin; model bir ya da daha fazla görsel döndürür. En güçlü yanları karmaşık prompt’ları anlaması ve stil çeşitliliğidir; bu da onu genel amaçlı text-to-image işleri için güçlü bir varsayılan tercih yapar.

## En uygun olduğu işler - Ayrıntılı bir metin açıklamasından fotogerçekçi sahneler ve portreler - Görsel içinde okunaklı metin, tabela ve tipografi basmak - Pek çok farklı estetikte konsept çizim, illüstrasyon ve stilize render’lar - Bir prompt’tan pazarlama görselleri, ürün mockup’ları ve sosyal medya görselleri - Prompt’a sadık kalmayı gerektiren karmaşık, çok özneli kompozisyonlar

## Şu durumlarda başka bir model seçin - Sıfırdan üretmek yerine mevcut bir görseli düzenlemek, yeniden tarzlamak ya da inpaint etmek istiyorsanız — bir görsel düzenleme modeli kullanın - Mevcut bir görseli büyütmeniz ya da ona detay eklemeniz gerekiyorsa — bir upscaling modeli kullanın - Video ya da animasyon gerekiyorsa — bir text-to-video modeli kullanın

## İpuçları - Özne, mekân, ışık ve stil konusunda net olun; SD 3.5 Large ayrıntılı prompt’ların karşılığını verir - Prompt’a daha sıkı uyum için `guidance_scale` değerini (varsayılan 3.5) 5-7 aralığına doğru yükseltin; daha fazla yaratıcı serbestlik için düşürün - İstenmeyen öğeleri dışarıda bırakmak için `negative_prompt` kullanın (ör. "blurry, extra fingers, watermark") - `image_size` alanına bir hazır ayar ("square_hd", "portrait_16_9", "landscape_4_3", …) verin ya da özel bir `{ width, height }` nesnesi geçin

## Gelişmiş Yapılandırma - `controlnet` — bir ControlNet model yolu ve bir `control_image_url` ile üretimi bir kontrol görseline (yapı/poz/kenarlar) göre koşullandırır. Yalnızca API üzerinden ayarlanır. - `ip_adapter` — bir IP-Adapter yolu üzerinden, isteğe bağlı olarak maskelenmiş bir referans görseli (`image_url`) üretime görsel prompt olarak verir. Yalnızca API üzerinden ayarlanır. - `loras` — özel stiller ya da özneler için bir veya daha fazla LoRA ağırlığı uygular (`path` ile, isteğe bağlı bir `scale` değeriyle). Yalnızca API üzerinden ayarlanır.

ModelRunner JavaScript client ile çalıştırmak için: ```js import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("stability-ai/stable-diffusion-v3.5-large", { input: { prompt: "a serene mountain lake at golden hour, mist over the water, photorealistic", image_size: "landscape_4_3", num_inference_steps: 28, guidance_scale: 3.5, }, }); ```

Stable Diffusion 3.5 Large API

Model girdisi

Input

Additional Settings

Model çıktısı

Output

Örnek istekler

Örnekler

Stable Diffusion 3.5 Large API

cURL

JavaScript

Python

Input parameters

Use Stable Diffusion 3.5 Large from Claude & Cursor (MCP)

MCP client config (Claude Desktop, Cursor)

Claude Code

Model Detayları

Model Detayları