How much does Stable Diffusion XL cost via Railwail?

Per-call: €0.20. No monthly minimum, no subscription. Start with €5 free credits.

What is the context window of Stable Diffusion XL?

Stable Diffusion XL supports a unknown context window — enough for typical AI workloads.

How fast is Stable Diffusion XL?

Average response latency: 8.0s (p50 across recent Railwail traffic). See live p50/p95 metrics on /rankings.

Is Stable Diffusion XL better than Flux 1.1 Pro Ultra?

It depends on your use case. Stable Diffusion XL (Stability AI) and Flux 1.1 Pro Ultra (Black Forest Labs) are both strong choices in image generation. Compare them side-by-side at /compare/stable-diffusion-xl-vs-flux-pro-ultra.

Stable Diffusion XL

Name: Stable Diffusion XL
Brand: Replicate
SKU: stable-diffusion-xl
Price: 0.2 EUR
Availability: InStock

Stability AI

Image Generation

Stability AI's SDXL model via Replicate. High-quality image generation with extensive customization.

Generate with Stable Diffusion XL

Describe what you want and pick a size — the image renders inline.

Size

Result appears here

TL;DR·Last updated March 4, 2026

Stable Diffusion XL is image generation AI model from Stability AI, priced at €0.000 per 1M input tokens with a unknown context window.

Try Stable Diffusion XL

Prompt

Aspect Ratio

Quality

Examples

See what Stable Diffusion XL can generate

Sample output

Anime Character

Prompt: "A fierce warrior princess with flowing silver hair and golden armor, standing atop a cliff overlooking a vast battlefield, anime art style, dramatic wind effects, detailed cel shading"

Sample output

Cozy Interior

Prompt: "A hygge-inspired reading nook with floor-to-ceiling bookshelves, a plush velvet armchair, warm fairy lights, a sleeping cat, and rain visible through a large arched window, digital painting style"

Sample output

Abstract Art

Prompt: "Geometric crystalline formations emerging from a pool of liquid gold, refracting rainbow light prisms throughout the composition, ultra-detailed 3D render with volumetric lighting and caustics"

Pricing

Price per Generation

Per generation€0.20

API Integration

Use our OpenAI-compatible API to integrate Stable Diffusion XL into your application.

Install

npm install railwail

JavaScript / TypeScript

import railwail from "railwail";

const rw = railwail("YOUR_API_KEY");

const images = await rw.run("stable-diffusion-xl", "A beautiful sunset over Tokyo");
console.log(images[0].url);

// Or use the image() method for full control
const res = await rw.image("stable-diffusion-xl", "A cat in space", {
  size: "1024x1024",
  n: 1,
});
console.log(res.data[0].url);

Specifications

Price

€0.20

Avg. latency

8.0s

Est. duration

Developer

Stability AI

Deep dive — Stability AI's Stable Diffusion XL

About Stability AI

Founded 2019 · London, UK

Stability AI was founded in 2019 by Emad Mostaque (CEO until March 2024) and is headquartered in London. The company sponsored and released the original Stable Diffusion 1.4/1.5/2.x (2022) in partnership with CompVis (LMU Munich, Robin Rombach and Patrick Esser), Runway and LAION. Stable Diffusion XL (SDXL) was released in July 2023 by Stability AI as a successor to SD 1.5/2.1 and was widely adopted by the open-source community as the de-facto open base model for fine-tuning and downstream pipelines until FLUX.1 and SD 3.5 arrived in 2024.

Visit Stability AI →

Architecture

Latent diffusion U-Net with two text encoders and optional refiner

Stable Diffusion XL (SDXL) is a 2023 latent diffusion model from Stability AI, described in 'SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis' (Podell et al. 2023). The architecture is a refined latent-diffusion U-Net operating in the latent space of a learned 8x VAE. Key changes over SD 1.5 include: (1) a larger U-Net backbone (~3.5B parameters, ~3x larger than SD 1.5), (2) two parallel text encoders concatenating CLIP ViT-L and OpenCLIP ViT-bigG features for stronger prompt adherence, (3) conditioning on the original image resolution and crop coordinates to fix the resolution and cropping artefacts of SD 1.5, (4) training natively at 1024x1024 instead of 512x512, and (5) an optional 6.6B-parameter refiner model that performs a final 5-step denoising pass to add high-frequency detail. SDXL became the dominant open base model for fine-tuning between mid-2023 and late 2024, spawning huge ecosystems including IP-Adapter, AnimateDiff, ControlNet-XL, T2I-Adapter and tens of thousands of community LoRAs.

Parameters: ~3.5B base U-Net + 6.6B refiner = ~10.1B total
Context: 75 tokens

What it can do

Native 1024x1024 generation
Two text encoders (CLIP-L + OpenCLIP-G) for strong prompts
Optional refiner for high-frequency detail
Open weights under CreativeML Open RAIL++-M license
Massive ecosystem: ControlNet-XL, IP-Adapter, AnimateDiff, LoRAs
Strong fine-tuning base for art styles and brand models
Runs on consumer GPUs (8-12GB VRAM with quantisation)
Best for: fine-tuning base, ControlNet pipelines, community LoRAs, on-prem deployments, education.

Training & License

Pretrained on a large subset of LAION-5B and additional Stability AI-curated data. Conditioned on resolution and crop coordinates to mitigate aspect-ratio artefacts.

License: CreativeML Open RAIL++-M license — open weights with usage restrictions (no NCII, CSAM, etc.). Commercial use permitted with these restrictions.

Known limitations