LLM Reference

Stable Diffusion XL

Released
2023-07-26
Last refreshed
2026-06-29
Status
Researched 135d ago
Open weightsCommercial use: conditionalMultimodalVision

Stable Diffusion XL is worth evaluating for vision when its provider route and context window match the workload.

Use it for

  • Teams evaluating vision
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Strict JSON or tool-calling flows
Specifications
Released
2023-07-26
Parameters
3K
Architecture
Diffusion
Specialization
image-generation
Openness
Open weights
License
Stability AI Community LicenseCommercial use: conditional
Weights
Available
Code
Unknown
Created by

Open-source generative AI models.

London, United Kingdom
Founded 2020
Website
Pricing
Output / 1M
-
Input / 1M
-

Cheapest of 1 route · Prodia

About

Stable Diffusion XL (SDXL) is Stability AI's large-scale image generation model, released July 2023. It features a two-stage pipeline (base model + optional refiner), dual text encoders (OpenCLIP and CLIP-L), and a larger UNet backbone producing higher-resolution, more detailed images than SD 1.5. SDXL became a widely used base for community fine-tunes and supports LoRA, ControlNet, and inpainting.

Top use-case fit

Vision

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Prodia--
ServerlessPartial

Capabilities

Multimodal

Benchmark peer barsfor Vision

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.