stable-diffusion-xl-base-1.0 vs SDXL-Lightning
Specs, VRAM requirements and download trends — updated 10 November 2026.
stabilityai · A · Open weights
Params
2.6 B
Context
—
30d
4.6 M
openrail++ licence · conditional
ByteDance · B · Open weights
Params
—
Context
—
30d
256 K
openrail++ licence · conditional
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | stable-diffusion-xl-base-1.0 | SDXL-Lightning |
|---|---|---|
| Parameters | 2.6 B | — |
| Architecture | — | — |
| Context length | — | — |
| Licence | openrail++ | openrail++ |
| Commercial use | Conditional | Conditional |
| Languages | — | — |
| Downloads 30d | 4,649,928 | 255,636 |
| Downloads all time | 131.4 M | 5.9 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2023-07-25 | 2024-02-20 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
4.7 M80 K
stable-diffusion-xl-base-1.0
SDXL-Lightning
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
stable-diffusion-xl-base-1.0 · fp16
39.7 GB / 24 GB
SDXL-Lightning · fp16
54.9 GB / 24 GB
Adjacent comparisons
Qwen-Image-2.1 vs stable-diffusion-xl-base-1.0
stable-diffusion-xl-base-1.0 vs Qwen-Image-2.1-Turbo-GGUF
stable-diffusion-xl-base-1.0 vs RealVisXL_V5.0
stable-diffusion-xl-base-1.0 vs animagine-xl-4.0
stable-diffusion-xl-base-1.0 vs Flux-2-Dev
stable-diffusion-xl-base-1.0 vs Qwen-Image-2.1-Uncensored-Quantized