Stable Diffusion XL

Name: Stable Diffusion XL
Brand: Stability AI
SKU: stable-diffusion-xl
Price: 0.0015 USD
Availability: InStock

Generiranje slikRazpoložljivo

od Stability AIstable-diffusion-xl

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

Preizkusi Pridobi API ključ Primerjaj

Cena: ≈ 0,0015 $/zagon
Vhod → Izhod: Besedilo → Slika
Razvijalec: Stability AI
Posodobljeno: 23. september 2026

Igrišče

Preizkusi Stable Diffusion XL

Vnos in rezultat

≈ 0,0015 $/zagon

Poziv

Napredne nastavitve (3)

Negativni poziv(izbirno)

Širina(izbirno)

Višina(izbirno)

⌘/Ctrl + Enter

Rezultat

Tvoja slika se pojavi tukaj.

Ta zagon

približno 0,0015 $ · 0,15 kreditov

Na začetku se rezervira 0,0044 $ (0,44 kreditov); obračunava se dejanski čas GPU.

Novo tukaj?

10 brezplačnih kreditov (0,10 $) ob prijavi z Googlom

Uporabno 24 ur po prijavi, do 5 zaganom na dan in največ 2 kreditov na zagon. Druge metode prijave se začnejo brez kreditov. Dovolj za 22 zagonov tega modela.

Examples

Real outputs from the public examples of this model on Replicate, with the prompt and settings that produced them. They were not generated live on this page.

Open full size
Prompt
An astronaut riding a rainbow unicorn, cinematic, dramatic
Settings
width

768
height

768
Open full size
Input
Prompt
A rainbow coloured bear
Settings
width

1024
height

1024
Open full size
Prompt
An astronaut riding a rainbow unicorn, cinematic, dramatic
Settings
width

1024
height

1024

Primeri pozivov

Primeri iz kataloga Railwail. Niso bili generirani v živo na tej strani.

Anime Character
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
Cozy Interior
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
Abstract Art
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

O Stable Diffusion XL

PovzetekOd 23. september 2026

Stable Diffusion XL je model razvijalca Stability AI iz kategorije Generiranje slik. Na Railwail stane Stable Diffusion XL ≈ 0,0015 $ na zagon.

Ozadje

O Stability AI

Ustanovljeno 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.

Obiščite Stability AI

Arhitektura

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.

Parametri: ~3.5B base U-Net + 6.6B refiner = ~10.1B total
Kontekst: 75 žetonov

Zmožnosti

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.

Usposabljanje in licenca

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.

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

Preizkusi varnosti: Stability AI applied baseline content filters and training data filtering. The model ships without an integrated safety classifier and operators must add their own moderation.

Znane omejitve

Older architecture — outperformed by FLUX.1 and SD 3.5 Large
Hands, text and complex anatomy imperfect
Default text encoder limited to 75 tokens
Open weights have no built-in safety filter

Raziskovalni članki

Cene

Cene v ameriških dolarjih. Uporaba se obračuna iz vnaprej plačanih kreditov.

Tipičen zagon (≈ 1 s na L40S)	0,0015 $ na zagon
Čas GPU (L40S)	0,00117 $ na sekundo GPU

Obračunan je čas GPU, ki ga zagon dejansko potrebuje. Ko se zagon začne, se od vašega stanja rezervira 3× tipična cena in se pozneje poravna.
1 kredit = 0,01 $

Kalkulator stroškov

Kalkulator cen

GPU-sekund na zagon

Tipično po ponudniku: približno 1,2 s

Zagoni

Skupaj

0,15 $

15 kreditov

Na zagon

0,0015 $ · 0,15 kreditov

Obračunava se dejanski čas GPU; to je ocena.

API

Pokličite Stable Diffusion XL s svojim Railwail API ključem. V zahtevku uporabite to ID modela:

stable-diffusion-xlDokumentacija API Pridobite API ključ

curl https://railwail.com/api/v1/images/generations \
  -H "Authorization: Bearer $RAILWAIL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "stable-diffusion-xl",
    "prompt": "A lighthouse on a rocky coast at sunset, photorealistic"
  }'

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["RAILWAIL_API_KEY"],
    base_url="https://railwail.com/api/v1",
)

image = client.images.generate(
    model="stable-diffusion-xl",
    prompt="A lighthouse on a rocky coast at sunset, photorealistic",
)

print(image.data[0].url)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.RAILWAIL_API_KEY,
  baseURL: "https://railwail.com/api/v1",
});

const image = await client.images.generate({
  model: "stable-diffusion-xl",
  prompt: "A lighthouse on a rocky coast at sunset, photorealistic"
});

console.log(image.data[0].url);

// npm install railwail
import railwail from "railwail";

const rw = railwail(process.env.RAILWAIL_API_KEY);

const res = await rw.image("stable-diffusion-xl", "A lighthouse on a rocky coast at sunset, photorealistic");

console.log(res.data[0].url);

Nastavite ključ kot RAILWAIL_API_KEYUstvari API ključ

Specifikacije

ID modela: stable-diffusion-xl
Razvijalec: Stability AI
Kategorija: Generiranje slik
Vhod: Besedilo
Izhod: Slika
Oblike izhoda: WEBP, JPG, PNG
Obračunavanje: Po porabi (žetoni ali čas GPU)
Velikost modela: ~3.5B base U-Net + 6.6B refiner = ~10.1B total
Licenca: CreativeML Open RAIL++-M license — open weights with usage restrictions (no NCII, CSAM, etc.). Commercial use permitted with these restrictions.
Kataložni vnos posodobljen: 23. september 2026

Vhodne parametre

Vhodi in nastavitve iz vhodne sheme modela. Primer v razdelku API prikazuje, katere od njih API sprejema.

ParameterTipPrivzetoDovoljene vrednosti

promptObvezno
Tip: Besedilo
Privzeto: –
Dovoljene vrednosti: –
width
Tip: Izbira
Privzeto: 1024
Dovoljene vrednosti: 512, 768 ali 1024
height
Tip: Izbira
Privzeto: 1024
Dovoljene vrednosti: 512, 768 ali 1024
negative_prompt
Tip: Besedilo
Privzeto: –
Dovoljene vrednosti: –

Oznake

open-source
customizable

Primeri uporabe

Kaj se uporablja za

Open-source creative pipelines (legacy)
Fine-tuning base for art-style models
ControlNet and IP-Adapter workflows
Community LoRA training
On-prem and air-gapped deployments
Educational and research use

Vsi modeli v Generiranje slik

Pogosta vprašanja

Kaj je Stable Diffusion XL?

Stable Diffusion XL je model podjetja Stability AI iz kategorije Generiranje slik. Na Railwailu ga lahko pokličete z ključem API prek Railwailovega API-ja.

Koliko stane Stable Diffusion XL na Railwailu?

Na Railwail stane Stable Diffusion XL ≈ 0,0015 $ na zagon. Zaračunano vam je tisto, kar vsaka zahteva dejansko porabi. Uporaba se plača s predplačanimi krediti; 1 kredit je enak 0,01 $.

Katere nastavitve podpira Stable Diffusion XL?

Glede na shemo vnosa Stable Diffusion XL pozna te parametre: prompt, width (512, 768 ali 1024), height (512, 768 ali 1024) in negative_prompt.

Kako hiter je Stable Diffusion XL?

Za Stable Diffusion XL je na Railwailu še premalo izmerjenih zagonov, da bi navedli čas izvajanja. Odvisno je od vnosa, nastavitev in obremenitve pri ponudniku.

Je Stable Diffusion XL boljši od FLUX 1.1 Pro?

To je odvisno od naloge. Stable Diffusion XL (Stability AI) in FLUX 1.1 Pro (Black Forest Labs) sta oba modela iz kategorije Generiranje slik. Stran za primerjavo prikazuje njune cene in specifikacije drug ob drugem.

Primerjaj Stable Diffusion XL in FLUX 1.1 Pro

Kako uporabljam Stable Diffusion XL prek API-ja?

Ustvarite ključ Railwailovega API-ja in pošljite zahtevo z ID-jem modela stable-diffusion-xl. Primeri kode za curl, Python in JavaScript so v razdelku API na tej strani.

Primerljivi modeli

Vsi v tej kategoriji

Icons (SDXL Flat Pop)Community
SDXL fine-tune by galleri5 for slick flat icons and pop constructivist graphics with thick edges. Trained on Bing generations, it produces clean single-subject icon art that suits app icons, badges and UI glyphs. Raster output, not true vector.
≈ 0,0094 $/zagon
527 % dražje na enoto
Primerjaj Stable Diffusion XL in Icons (SDXL Flat Pop)
InstantIDCommunity
InstantID makes realistic portraits of a real person from a single reference photo without per-user training. Combines a face encoder with an IdentityNet adapter on SDXL to keep identity and pose while following a text prompt, so it is fast and tuning-free.
≈ 0,084 $/zagon
5500 % dražje na enoto
Primerjaj Stable Diffusion XL in InstantID
Sticker MakerCommunity
fofr's sticker generator that outputs graphics with transparent backgrounds, so the result drops straight into chat apps or print sheets. Runs an SDXL-based pipeline at high speed (default 17 steps) and returns die-cut style art without manual background removal.
≈ 0,0055 $/zagon
267 % dražje na enoto
Primerjaj Stable Diffusion XL in Sticker Maker

Uporabite Stable Diffusion XL prek API

En API ključ za vsak model na Railwail. Uporaba se obračuna iz vnaprej plačanih kreditov, 1 kredit = 0,01 $.

Pridobite API ključ Oglejte si vse modele