SDXL-Lightning
No estimate
No hardware requirements for this model
This model's weights are open, but no parameter count has been published for it. Every memory and speed figure starts from that number, so we would rather show nothing than a fabricated estimate.
On record
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- ByteDance
- Organisation type
- Industry
- Country
- China
- Published
- 24 February 2024
- Authors
- Shanchuan Lin, Anran Wang, Xiao Yang
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Image generation
- Task
- Image generation, Text-to-image
- Base model
- Stable Diffusion XL (SDXL)
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Training data
- tokens
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Training hardware
- NVIDIA A100 SXM4 80 GB
- Chips used
- 64
- Power draw
- 50.7 kW
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Open — downloadable
- Model access
- Open weights (restricted use)
- Training code
- Unreleased
- Hugging Face
- ByteDance
Openrail++ license https://huggingface.co/ByteDance/SDXL-Lightning
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Unknown
Sources
Where this record came from and when it was last checked.
- Reference
- SDXL-Lightning: Progressive Adversarial Diffusion Distillation
- Last updated
- 28 November 2025
What the numbers mean
About this model
SDXL-Lightning was published by ByteDance, in the country recorded as China, during February 2024. The publishing organisation is categorised as industry.
It works in the domain of Image generation, and is recorded as performing the task of image generation, Text-to-image.
It builds on Stable Diffusion XL (SDXL). That is the usual way a specialised model is produced.
The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold. On Hugging Face it is published under the organisation ByteDance.
Answers
SDXL-Lightning — common questions
SDXL-Lightning— what is it used for?
It works in the domain of Image generation, and is recorded as handling the task of image generation, Text-to-image. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
SDXL-Lightning— where can I download it?
Its weights are published on Hugging Face, under the organisation ByteDance. We do not host model files — this site calculates what hardware is needed to run them.
SDXL-Lightning— what GPU do I need to run it?
We cannot say. It has open weights, but no parameter count has been published for it, and every memory and speed calculation starts from that number. We would rather show nothing than a fabricated estimate.
SDXL-Lightning— is it open source?
Its weights are published, so it can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.
SDXL-Lightning— how many parameters does it have?
No parameter count has been published for it, which is why no memory or speed figure appears on this page.
SDXL-Lightning— who created it?
It was published by ByteDance, based in China, an organisation categorised as industry.
SDXL-Lightning— when was it released?
It was published in February 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.