---
license: creativeml-openrail-m
language:
- en
library_name: diffusers
pipeline_tag: text-to-image
base_model: stabilityai/stable-diffusion-xl-base-1.0
tags:
- stable-diffusion
- stable-diffusion-xl
- sdxl
- sdxl-lightning
- text-to-image
- photorealistic
- fast
- low-step
- juggernaut
- rundiffusion
- kandooai
---
> Juggernaut XL Lightning is the **speed-optimized** member of the Juggernaut family — built on **SDXL Lightning** distillation, it produces photo-grade Juggernaut output in just **5–7 inference steps** instead of the usual 30–40. Same aesthetic, ~5× faster, ideal for batch generation, real-time iteration, and live demos.
## When to Use It
- ⚡ **Batch generation** — render hundreds of variations in the time you'd usually generate a few.
- 🔁 **Real-time iteration** — preview prompt changes in seconds, not minutes.
- 💻 **Lower-end hardware** — fewer steps means lower VRAM pressure during inference.
- 🎤 **Live demos and showcases** — instant turnaround when latency is the bottleneck.
If you need the very best per-image quality and don't mind the wait, use [**Juggernaut XL v9**](https://huggingface.co/RunDiffusion/Juggernaut-XL-v9) instead — full-step inference holds slightly more detail.
---
⚡ Want speed without setup? Run Lightning on RunDiffusion.
Pre-loaded with the right scheduler, sampler, and CFG. No installs. No GPU rental.
Pre-loaded into ComfyUI · Forge · Automatic1111 · Fooocus · InvokeAI · SwarmUI
---
## Recommended Settings
> **These are different from standard Juggernaut.** Lightning needs fewer steps and lower CFG.
| Parameter | Value |
| --- | --- |
| Sampler | `DPM++ SDE` or `DPM++ SDE Karras` |
| Steps | `5 – 7` |
| CFG scale | `1.5 – 2.0` |
| Resolution | `≥ 1024 × 1024` (use SDXL-native sizes) |
| VAE | **Already baked in** — no external VAE required |
Standard Juggernaut prompts work as-is. Don't adjust your prompt for Lightning — just adjust the sampler, steps, and CFG.
📖 **Want to go deeper on prompting?** See the [**RunDiffusion prompting library**](https://www.rundiffusion.com/prompting?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_lightning&utm_content=prompting_inline). Free to read, no signup.
## Two Ways to Run Juggernaut XL Lightning
### 🚀 Easiest — Run it on RunDiffusion (recommended)
One-click access inside ComfyUI, Forge, Automatic1111, Fooocus, InvokeAI, or SwarmUI. **Free trial included**, plus access to every other Juggernaut model on the same account.
### 💻 Or run it locally — Diffusers
```python
import torch
from diffusers import DiffusionPipeline, DPMSolverSinglestepScheduler
pipe = DiffusionPipeline.from_pretrained(
"RunDiffusion/Juggernaut-XL-Lightning",
torch_dtype=torch.float16,
use_safetensors=True,
).to("cuda")
# DPM++ SDE Karras
pipe.scheduler = DPMSolverSinglestepScheduler.from_config(
pipe.scheduler.config, use_karras_sigmas=True
)
prompt = "Cinematic mid shot photo of an astronaut walking through a neon-lit Tokyo alley at night, hyperdetailed photography, skin details, shallow depth of field"
image = pipe(prompt, width=1024, height=1024, num_inference_steps=6, guidance_scale=1.8).images[0]
image.save("juggernaut_xl_lightning.png")
```
For ComfyUI / Forge / InvokeAI / SwarmUI: download the single-file checkpoint and drop it into your `models/checkpoints/` directory.
## The Rest of the Family
| Model | Best for |
| --- | --- |
| [**Juggernaut XL v9**](https://huggingface.co/RunDiffusion/Juggernaut-XL-v9) | The flagship SDXL — full-step photorealism workhorse. **6M+ downloads.** |
| [**Juggernaut XI v11**](https://huggingface.co/RunDiffusion/Juggernaut-XI-v11) | Latest SDXL-line refinement |
| [**Juggernaut XI Lightning**](https://huggingface.co/RunDiffusion/Juggernaut-XI-Lightning) | Speed variant on the XI base |
| [**Juggernaut Z**](https://huggingface.co/RunDiffusion/Juggernaut-Z-Image) | Lumina-Image-2 architecture — cinematic, presentation-ready |
| [**Juggernaut Pro Flux**](https://www.rundiffusion.com/juggernaut-pro-flux?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_lightning&utm_content=cross_promo_pro_flux) | FLUX.1 backbone — top-tier photo quality |
## Commercial Use
This model **may not be deployed behind paid API services** without explicit licensing. For commercial licensing, custom models, business inquiries, or consultation, contact **[juggernaut@rundiffusion.com](mailto:juggernaut@rundiffusion.com)**.
You are free to use this model for personal and creative work under the terms of the [CreativeML Open RAIL-M license](https://huggingface.co/spaces/CompVis/stable-diffusion-license).
## Credits
Juggernaut XL Lightning was created by **[KandooAI](https://twitter.com/Juggernaut_AI)** in collaboration with **[RunDiffusion](https://www.rundiffusion.com/?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_lightning&utm_content=credits)**, distilled on top of **[SDXL Lightning](https://huggingface.co/ByteDance/SDXL-Lightning)**.
---
