← All models

Stable Diffusion XL 1.0

Image Available

stability-ai/sdxl · by Stability AI · Latent diffusion

Pricing — 1 offering(s)

Replicate

View on Replicate ↗

A100 80GB (compute-billed)

$0.0032 / second Historical 2023-07-26 → 2023-08-15 · Nvidia A100 (80GB)
$0.0014 / second Current 2023-08-16 → present · Nvidia A100 (80GB)

Showing the active price and any recorded history. Full pricing history is available via the paid API — see API docs.

Capability profile

Artistic style range strong

Photorealism strong

Prompt adherence moderate

Compositional accuracy moderate

Text rendering weak

Resolution ceiling moderate

Inference speed moderate

Benchmarks

Benchmark	Score	Config	Source
GenEval	0.55	SDXL overall GenEval as reported in the GenEval paper; also echoed in later comparison tables.	paper ↗

Operator guidance

Route here when you need open weights, fine-tuning/LoRA control, or self-hosting economics. Step up to DALL·E 3 or FLUX for prompt adherence and in-image text; SDXL is the weakest of the three on text and complex composition.

Use cases

Self-hosted / open-weight deployments and on-prem economics
Style and domain customisation via LoRA / fine-tuning
Cost-controlled, compute-billed batch generation
Photoreal work when paired with the refiner and upscaling

Provenance notice

Open weights under a RAIL licence carrying use-based restrictions
No built-in content-provenance metadata by default

Limitations

Weak in-image text rendering
Lower prompt adherence (GenEval 0.55) than DALL·E 3 / FLUX
Needs the refiner and/or upscaling for top-end fidelity
No meaningfully comparable cross-vendor FID / CLIPScore is published