Model reference · open weights
SDXL-Lightning is an open-weight image model from ByteDance, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
SDXL-Lightning SDXL-Lightning is a lightning-fast text-to-image generation model. It can generate high-quality 1024px images in a few steps. For more information, please refer to our research paper: SDXL-Lightning: Progressive Adversarial Diffusion Distillation. We open-source the model as part of the research. Our models are distilled from stabilityai/stable-diffusion-xl-base-1.0. This repository contains checkpoints for 1-step, 2-step, 4-step, and 8-step distilled models. The generation quality of our 2-step, 4-step, and 8-step model is amazing. Our 1-step model is more experimental. We provide both full UNet and LoRA checkpoints. The full UNet models have the best quality while the LoRA models can be applied to other base models. Demos Generate with all configurations, best quality: Demo Checkpoints sdxllightningNstep.safetensors: All-in-one checkpoint, for ComfyUI. sdxllightningNstepunet.safetensors: UNet checkpoint only, for Diffusers. sdxllightningNsteplora.safetensors: LoRA checkpoint, for Diffusers and ComfyUI. Diffusers Usage Please always use the correct checkpoint for the corresponding inference steps. 2-Step, 4-Step, 8-Step UNet 2-Step, 4-Step, 8-Step LoRA Use LoRA only if you are using non-SDXL base models. Otherwise use our UNet checkpoint for better quality. 1-Step UNet The 1-step model is only experimental and the quality is much less stable. Consider using the 2-step model for much better quality. The 1-step model uses "sample" prediction instead of "epsilon" prediction! The scheduler needs to be configured correctly. ComfyUI Usage Please always use the correct checkpoint for the corresponding inference steps. Please use Euler sampler with sgmuniform scheduler. 2-Step, 4-Step, 8-Step Full 1. Download the full checkpoint (sdxllightningNstep.safetensors) to /ComfyUI/models/checkpoints. 1. Download our ComfyUI full workflow. 2-Step, 4-Step, 8-Step LoRA Use LoRA only if you are using non-SDXL base models. Otherwise use our full checkpoint for better quality. 1. Prepare your own base model. 1. Download the LoRA checkpoint (sdxllightningNsteplora.safetensors) to /ComfyUI/models/loras 1. Download our ComfyUI LoRA workflow. 1-Step The 1-step model is on
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | ByteDance |
|---|---|
| Type | Image models |
| Variants | 1 |
| Runs with | diffusers |
| Released | 2024-02-20 |
| Popularity | 86k downloads / month |
| Likes | 2,182 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| SDXL-Lightning | — | BF16 | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys sdxl-lightning for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (sdxl-lightning below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/images/generations \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"sdxl-lightning","prompt":"a red bicycle","size":"1024x1024"}'
Licence
Open weights under openrail++ — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗