Project AURIONAI Use-Cases Research & Innovation
ByteDance
image generation

SDXL-Lightning

Few-step text-to-image model distilled from SDXL that generates 1024px images in one to eight steps.

ByteDanceByteDanceChina
Grid of images generated by SDXL-Lightning.
Levelmodel
Classimage generation
Parametersnot in the notes
Contextnot in the notes
Released20 Feb 2024
Opennessopen weights restricted
Runs onconsumer GPU
Statusactive

Lineage

distillfinetune
SDXL to SDXL-Lightning: distill, high confidenceSDXL to Juggernaut-XL v9: finetune, high confidenceSDXLSDXLStability AIJuggernaut-XL v9Juggernaut-XL v9Feb 2024SDXL-LightningSDXL-LightningByteDance, Feb 2024
Stability AISDXL is the parent (distill)high confidencenotes
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 3 models. Confidence and evidence are the notes' own.

R&D Topics

Few-step distillation of diffusion modelsexemplar

Identity

Developer
ByteDance
Family
not in the notes
Released
20 Feb 2024 sourcesregistry date
Weights published
20 Feb 2024
Record checked
12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
diffusion SDXL distilled with progressive adversarial diffusion distillation
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
text
Output
image
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
open weights restricted
Licence
OpenRAIL++ sources
Access routes
open weights download, API
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
consumer GPU
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/abs/2402.13929 https://arxiv.org/abs/2402.13929
  2. huggingface.co/ByteDance/SDXL-Lightning https://huggingface.co/ByteDance/SDXL-Lightning
  3. replicate.com/bytedance/sdxl-lightning-4step https://replicate.com/bytedance/sdxl-lightning-4step

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "SDXL-Lightning", https://aurion.semai.id/models/bytedance-sdxl-lightning/, records of October 2026.