# Stable Diffusion 3.5 Large

> Stability AI's 8.1-billion parameter Multimodal Diffusion Transformer (MMDiT) text-to-image model featuring improved image quality, typography, complex prompt understanding, and resource-efficiency

## Quick Reference

- Model ID: stable-diffusion-3.5-large
- Creator: Stability AI
- Status: active
- Family: stable-diffusion-3.5
- Base URL: https://api.lumenfall.ai/openai/v1

## Specifications

- Max Resolution: 1024x1024
- Input Modalities: text
- Output Modalities: image
- Supported Modes: Text to Image, Image Edit

## API Parameters

The compiled parameter schema for this model is available via the API: `GET /v1/models/stable-diffusion-3.5-large?schema=true`.

### Core Parameters

- `prompt` (string) — REQUIRED: Text prompt for image generation. Modes: Text to Image, Image Edit
- `negative_prompt` (string): Negative prompt to guide generation away from undesired content. Modes: Text to Image, Image Edit
- `seed` (integer): Random seed for reproducibility. Modes: Text to Image, Image Edit

### Size & Layout

- `size` (string): Image dimensions as WxH pixels (e.g. "1024x1024") or aspect ratio (e.g. "16:9"). Values: 1563x670, 670x1564, 1365x768, 768x1365, 1254x836, 836x1254, 1024x1024, 1145x916, 916x1145. Modes: Text to Image, Image Edit
- `aspect_ratio` (string): Aspect ratio of the output image (e.g. "16:9", "1:1"). Values: 9:21, 9:16, 2:3, 4:5, 1:1, 5:4, 3:2, 16:9, 21:9. Modes: Text to Image, Image Edit
- `resolution` (string): Output resolution tier (e.g. "1K", "4K"). Values: 1K. Modes: Text to Image, Image Edit

### Media Inputs

- `image` (file) — REQUIRED: Input image(s) to edit. Modes: Image Edit

### Output & Format

- `response_format` (string): How to return the image. Default: url. Values: url, b64_json. Modes: Text to Image, Image Edit
- `output_format` (string): Output image format. Values: png, jpeg, gif, webp, avif. Modes: Text to Image, Image Edit
- `output_compression` (integer): Compression level for lossy formats (JPEG, WebP, AVIF). Modes: Text to Image, Image Edit
- `n` (integer): Number of images to generate. Default: 1. Modes: Text to Image, Image Edit

### Additional Parameters

- `cfg_scale` (number): Classifier-free guidance scale — higher values stick more closely to the prompt. Modes: Text to Image, Image Edit
- `strength` (number): How much to transform the input image: 0 keeps it unchanged, 1 fully regenerates from the prompt. Modes: Image Edit
- `controlnet` (object): ControlNet for inference.. Modes: Text to Image. Only available via fal
- `enable_safety_checker` (boolean): If set to true, the safety checker will be enabled.. Modes: Text to Image. Only available via fal
- `ip_adapter` (object): IP-Adapter to use during inference.. Modes: Text to Image. Only available via fal
- `loras` (array): The LoRAs to use for the image generation. You can use any number of LoRAs and they will be merged together to generate the final image.. Modes: Text to Image. Only available via fal
- `num_inference_steps` (integer): The number of inference steps to perform.. Modes: Text to Image. Only available via fal
- `sync_mode` (boolean): If `True`, the media will be returned as a data URI and the output data won't be available in the request history.. Modes: Text to Image. Only available via fal


## Model Identifiers

- Primary Slug: stable-diffusion-3.5-large

## Dates

- Released: October 2024

## Tags

image-generation, text-to-image, open-weights

## Available Providers

### fal.ai

- Config Key: fal/stable-diffusion-3.5-large
- Provider Model ID: fal-ai/stable-diffusion-v35-large
- Pricing: $0.065/megapixel
  - Source: https://fal.ai/models/fal-ai/stable-diffusion-v35-large

### Replicate

- Config Key: replicate/stable-diffusion-3.5-large
- Provider Model ID: stability-ai/stable-diffusion-3.5-large
- Pricing: $0.065/image
  - Source: https://replicate.com/stability-ai/stable-diffusion-3.5-large


## Performance Metrics

Provider performance over the last 30 days.

### replicate

- Median Generation Time (p50): 11706ms
- 95th Percentile Generation Time (p95): 13476ms
- Average Generation Time: 11655ms
- Success Rate: 100.0%
- Total Requests: 12
- Time to First Byte (p50): 11197ms
- Time to First Byte (p95): 11611ms


## Arena Benchmarks

### Fantasy Warrior

- Elo: 1233
- Record: 14W / 29L / 3T (46 battles)
- Rank: #10 of 71

### Apollo 11: Journey to Tranquility

- Elo: 1230
- Record: 32W / 22L / 2T (56 battles)
- Rank: #7 of 70

### Vintage Cafe Logo

- Elo: 1228
- Record: 15W / 40L / 0T (55 battles)
- Rank: #6 of 70

### Victorian Greenhouse Oasis

- Elo: 1214
- Record: 21W / 32L / 3T (56 battles)
- Rank: #6 of 17

### Isometric Miniature Diorama Scenes

- Elo: 1199
- Record: 25W / 25L / 2T (52 battles)
- Rank: #16 of 72

### Modern Clean Menu

- Elo: 1198
- Record: 21W / 23L / 1T (45 battles)
- Rank: #11 of 69

### Geometric Composition

- Elo: 1164
- Record: 15W / 35L / 1T (51 battles)
- Rank: #24 of 70

### Adorable Baby Animals in Sunny Meadow

- Elo: 1154
- Record: 9W / 40L / 1T (50 battles)
- Rank: #23 of 72

### Intricate Floral Mandala

- Elo: 1140
- Record: 10W / 33L / 1T (44 battles)
- Rank: #14 of 15

### Candid Street Photography

- Elo: 1133
- Record: 11W / 29L / 4T (44 battles)
- Rank: #26 of 68

### Heroic Super Hero Portrait

- Elo: 1122
- Record: 4W / 55L / 1T (60 battles)
- Rank: #19 of 21


## Use Cases & Category Performance

### Product, Branding & Commercial (Text-to-Image)

- Rank: #17 of 56
- Elo: 1220
- Record: 68W / 85L / 3T (156 battles)
- Win Rate: 43.6%

### Text Rendering (Text-to-Image)

- Rank: #18 of 58
- Elo: 1224
- Record: 93W / 110L / 5T (208 battles)
- Win Rate: 44.7%

### Creativity (Text-to-Image)

- Rank: #21 of 56
- Elo: 1220
- Record: 86W / 116L / 7T (209 battles)
- Win Rate: 41.1%

### Prompt Adherence (Text-to-Image)

- Rank: #24 of 60
- Elo: 1223
- Record: 102W / 145L / 7T (254 battles)
- Win Rate: 40.2%

### Aesthetics (Text-to-Image)

- Rank: #29 of 62
- Elo: 1214
- Record: 110W / 221L / 12T (343 battles)
- Win Rate: 32.1%

### 3D Imaging & Modeling (Text-to-Image)

- Rank: #15 of 29
- Elo: 1218
- Record: 40W / 60L / 3T (103 battles)
- Win Rate: 38.8%

### Photorealism (Text-to-Image)

- Rank: #37 of 61
- Elo: 1158
- Record: 49W / 133L / 9T (191 battles)
- Win Rate: 25.7%

### Portraits (Text-to-Image)

- Rank: #18 of 24
- Elo: 1153
- Record: 14W / 29L / 3T (46 battles)
- Win Rate: 30.4%

### Cartoon, Anime & Fantasy (Text-to-Image)

- Rank: #18 of 24
- Elo: 1153
- Record: 14W / 29L / 3T (46 battles)
- Win Rate: 30.4%


## Image Gallery

14 images available for this model. Browse all at https://lumenfall.ai/models/stability-ai/stable-diffusion-3.5-large/gallery

### Curated Examples

- [Cinematic wide shot of a high-end, minimalist flagship store in a bustling metropolitan district ...](https://assets.lumenfall.ai/wOFafmVLYqUuDPwL_E7ZpJVbF-1-SXVYRgJMNXg__iw/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/4ie4s6h8fcmb6xdoglh0jximkp9i@jpeg)
- [A portrait of an elderly artisan in a sun-drenched Mediterranean workshop, meticulously hand-pain...](https://assets.lumenfall.ai/x7yApOPZHhyivlSidhL8u-IlTfVrRdfmjIxRO6CDFYI/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/z02pkd7pbn7ry3rtpvo3mert0da2@jpeg)
- [A cozy street-side bakery with a chalkboard sign out front that reads "FRESH SOURDOUGH" in elegan...](https://assets.lumenfall.ai/kTZYzXb5fWDOS2jwAh85gD8svu8KhG9uql63t3PHdJg/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/jyb7x1gbk6vgn1xcsbtw9wml376t@jpeg)

### Arena Competition Results

- [Fantasy Warrior](https://assets.lumenfall.ai/jXzPSJXH-jChlFbAXLq9SQ9FTm06yDCFfF5uCvjLgn0/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/pe2bzlgtvkowppfcqvkz8pqb288a@jpeg): #10 of 71 (Elo 1233)
- [Apollo 11: Journey to Tranquility](https://assets.lumenfall.ai/y3ScnKT7AVPnN7GROLN_s2Ujy8r1m44hYc6I4zrYWu8/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/90ihft3stu1lx9uou2jzzmyhmcqw@jpeg): #7 of 70 (Elo 1230)
- [Vintage Cafe Logo](https://assets.lumenfall.ai/v5QqeUw3VylWSgfCihWi21Z8B0EO7lHEnqNHLBcTdP8/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/rbrkfqa1wjhhs3mznjxxstkog3oy@jpeg): #6 of 70 (Elo 1228)
- [Victorian Greenhouse Oasis](https://assets.lumenfall.ai/amR1gcZt6dcWlKZptAwCt7OAUEf6CkiP4E9WcWF20RM/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/0sxyodlh9i5l42aqkbgyx8qs4xk2@jpeg): #6 of 17 (Elo 1214)
- [Isometric Miniature Diorama Scenes](https://assets.lumenfall.ai/UDnu4rEn7nz6lnZJntRL3CqK5GPmlQ92z6iqUbr4Ohk/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/n1r09mmuk423qtbnn29xnnqxge32@jpeg): #16 of 72 (Elo 1199)
- [Modern Clean Menu](https://assets.lumenfall.ai/zkQTLKA46e8jyLUWLx_KD9i-s8SCGotPGM7kfdf-o0o/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/jn9xil63h9udhb562o9l6dg5zvah@jpeg): #11 of 69 (Elo 1198)
- [Geometric Composition](https://assets.lumenfall.ai/gea_-mepft6g2oDGecMp9aPw0XIfAOve9Tn2EhTiu-4/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/pcouf2kufexf31v3c9ub2j0fe4jn@jpeg): #24 of 70 (Elo 1164)
- [Adorable Baby Animals in Sunny Meadow](https://assets.lumenfall.ai/aZzMky_rB33fZoBD9ZZMYcZ2CC1xw24360-HEbmaS_0/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/01ihq91bwcseuc5z9fomkzofwqbi@jpeg): #24 of 72 (Elo 1154)
- [Intricate Floral Mandala](https://assets.lumenfall.ai/FyUKL_-WtHtqpYR0nUxwgTFprjpUNd8j1mYhoM28IcA/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/4q3jdkc00eeymww12a0mqumemfz5@jpeg): #14 of 15 (Elo 1140)
- [Candid Street Photography](https://assets.lumenfall.ai/p2xtIUYj5e4GoLU3LnTHmP0f8mQazY-hi_aw9Hw1lKw/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/zo2l8cj5n5ubmpnstfzbr2tnsyda@jpeg): #26 of 68 (Elo 1133)
- [Heroic Super Hero Portrait](https://assets.lumenfall.ai/Y0KEKpNCz7xbqXtKEU4_4y_R-aniYZYfvZTTeO4ahuQ/rs:fit:1500:1500/plain/gs://lumenfall-prod-assets/aazjrm9yvsl3g7zo5u3dibby4ksc@jpeg): #19 of 21 (Elo 1122)

## Example Prompt

The following prompt was used to generate an example image in our playground:

A cozy street-side bakery with a chalkboard sign out front that reads "FRESH SOURDOUGH" in elegant cursive. A tiny capybara is peaking out from behind a stack of flour sacks in the sun-drenched corner of the shop window. 35mm photography.

## Code Examples

### Text to Image (/v1/images/generations)

#### cURL

curl -X POST \
  https://api.lumenfall.ai/openai/v1/images/generations \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "stable-diffusion-3.5-large",
    "prompt": "",
    "size": "1024x1024"
  }'

# Response:
# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }

#### JavaScript

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.lumenfall.ai/openai/v1'
});

const response = await client.images.generate({
  model: 'stable-diffusion-3.5-large',
  prompt: '',
  size: '1024x1024'
});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
console.log(response.data[0].url);

#### Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.lumenfall.ai/openai/v1"
)

response = client.images.generate(
    model="stable-diffusion-3.5-large",
    prompt="",
    size="1024x1024"
)

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
print(response.data[0].url)

### Image Edit (/v1/images/edits)

#### cURL

curl -X POST \
  https://api.lumenfall.ai/openai/v1/images/edits \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -F "model=stable-diffusion-3.5-large" \
  -F "image=@source.png" \
  -F "prompt=Add a starry night sky to this image" \
  -F "size=1024x1024"

# Response:
# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }

#### JavaScript

import OpenAI from 'openai';
import fs from 'fs';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.lumenfall.ai/openai/v1'
});

const response = await client.images.edit({
  model: 'stable-diffusion-3.5-large',
  image: fs.createReadStream('source.png'),
  prompt: 'Add a starry night sky to this image',
  size: '1024x1024'
});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
console.log(response.data[0].url);

#### Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.lumenfall.ai/openai/v1"
)

response = client.images.edit(
    model="stable-diffusion-3.5-large",
    image=open("source.png", "rb"),
    prompt="Add a starry night sky to this image",
    size="1024x1024"
)

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
print(response.data[0].url)


## About

## Overview
Stable Diffusion 3.5 Large is an 8.1-billion parameter text-to-image model developed by Stability AI. Built on the Multimodal Diffusion Transformer (MMDiT) architecture, it is designed to balance high-fidelity visual output with the ability to follow intricate, multi-part natural language instructions. This model represents a significant refinement in the Stable Diffusion lineage, focusing on improved prompt adherence and photorealism compared to its predecessors.

## Strengths
*   **Complex Prompt Adherence:** The model excels at interpreting long, descriptive prompts that include specific spatial relationships, multiple subjects, and detailed stylistic instructions.
*   **Typography and Text Rendering:** It demonstrates a high degree of accuracy when generating legible text within images, minimizing the spelling errors common in earlier latent diffusion models.
*   **Subject Diversity:** It is capable of generating a wide range of human skin tones, textures, and facial features without a strong inherent bias toward a single aesthetic style.
*   **Structural Composition:** The MMDiT architecture allows the model to maintain better global consistency, ensuring that large-scale elements (like limbs or architectural features) are proportionally correct and logically placed.

## Limitations
*   **Hardware Requirements:** At 8.1 billion parameters, it requires significant VRAM for local inference, making it less suitable for consumer-grade hardware without quantization.
*   **Generation Speed:** Due to its size and the complexity of the transformer-based backbone, it generally has higher latency per image compared to "Turbo" or "Lightning" versions of the SD3 family.
*   **Anatomical Edge Cases:** While improved, the model can still struggle with extremely complex anatomical poses or highly overlapping human figures in crowded scenes.

## Technical Background
The model utilizes a Multimodal Diffusion Transformer (MMDiT) architecture, which uses separate sets of weights for image and text representations but allows them to interact via a bidirectional flow of information. This approach enables the model to treat visual and textual data as equal contributors to the final output, improving the alignment between the user's input and the generated pixels. The training process prioritized resource efficiency and stable convergence, allowing the 8.1B parameter model to outperform larger competitors in specific benchmark categories.

## Best For
Stable Diffusion 3.5 Large is ideal for professional design workflows where precise control over composition and text is required, such as creating posters, book covers, or conceptual art from detailed briefs. It is a strong choice for users who need a versatile, general-purpose model that can handle both photorealistic and stylized requests without extensive fine-tuning. 

This model is available for testing and integration through Lumenfall's unified API and playground, allowing you to compare its output alongside other industry-standard image generation models.

## Frequently Asked Questions

### How much does Stable Diffusion 3.5 Large cost?

Stable Diffusion 3.5 Large starts at $0.065 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.

### How do I use Stable Diffusion 3.5 Large via API?

You can use Stable Diffusion 3.5 Large through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "stable-diffusion-3.5-large". Code examples are available in Python, JavaScript, and cURL.

### Which providers offer Stable Diffusion 3.5 Large?

Stable Diffusion 3.5 Large is available through fal.ai and Replicate on Lumenfall. Lumenfall automatically routes requests to the best available provider.

### What is the maximum resolution for Stable Diffusion 3.5 Large?

Stable Diffusion 3.5 Large supports images up to 1024x1024 resolution.

## Links

- Model Page: https://lumenfall.ai/models/stability-ai/stable-diffusion-3.5-large
- About: https://lumenfall.ai/models/stability-ai/stable-diffusion-3.5-large/about
- Providers, Pricing & Performance: https://lumenfall.ai/models/stability-ai/stable-diffusion-3.5-large/providers
- API Reference: https://lumenfall.ai/models/stability-ai/stable-diffusion-3.5-large/api
- Benchmarks: https://lumenfall.ai/models/stability-ai/stable-diffusion-3.5-large/benchmarks
- Use Cases: https://lumenfall.ai/models/stability-ai/stable-diffusion-3.5-large/use-cases
- Gallery: https://lumenfall.ai/models/stability-ai/stable-diffusion-3.5-large/gallery
- Playground: https://lumenfall.ai/models/stability-ai/stable-diffusion-3.5-large/playground
- API Documentation: https://docs.lumenfall.ai