license: cc-by-nc-nd-4.0
language:
- en
library_name: diffusers
pipeline_tag: text-to-image
base_model: stabilityai/stable-diffusion-xl-base-1.0
extra_gated_prompt: >
By accessing this model, you agree to the following:
- You will NOT deploy this model behind a paid API or generative service.
- You will NOT use this model on a platform that competes with
RunDiffusion.com.
- You will NOT redistribute or rehost the model weights.
- You agree to receive communications from RunDiffusion (model releases,
platform updates, and news). RunDiffusion does not misuse your information.
Commercial licenses can be obtained by emailing juggernaut@rundiffusion.com.
extra_gated_fields:
Name: text
Email: text
Intended use: text
tags:
- stable-diffusion
- stable-diffusion-xl
- sdxl
- sdxl-lightning
- text-to-image
- photorealistic
- fast
- low-step
- juggernaut
- rundiffusion
- kandooai
Juggernaut XI Lightning by RunDiffusion
The latest XI quality at SDXL Lightning speed — 5–7 steps, photo-grade output.
Juggernaut XI Lightning is the speed-optimized variant of Juggernaut XI v11 — distilled with SDXL Lightning for 5–7-step inference. All of XI's improvements (sharper hands, faces, better prompt adherence, native text rendering) at ~5× the speed of standard XI.
Inherited from XI v11
- 🎨 Massively improved aesthetics over X / earlier versions
- 🖐️ Better hands, eyes, faces, and overall human anatomy
- 🎯 Stronger prompt adherence
- 🔤 Native text rendering for signage, labels, short phrases
- 💬 Two prompting styles: Natural language or Tagging
- 🖼️ RunDiffusion Photo refinement
What Lightning Adds
- ⚡ 5–7-step inference — generate in a fraction of standard SDXL inference time
- 🔁 Real-time iteration — preview prompt changes in seconds
- 💻 Lower VRAM pressure during inference
If you need the very best per-image quality, use the standard XI v11 instead.
⚡ Skip the gated download. Try XI Lightning in your browser.
No HF gate. No installs. No GPU rental. Just generate at speed.
Pre-loaded into ComfyUI · Forge · Automatic1111 · Fooocus · InvokeAI · SwarmUI
Recommended Settings
Lightning needs different settings from standard XI. Steps low, CFG very low.
| 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 XI prompts work as-is. Just adjust the sampler, steps, and CFG.
📖 Prompting library — free to read.
The Rest of the Family
| Model | Best for |
|---|---|
| Juggernaut XI v11 | Standard XI — full-step, maximum detail |
| Juggernaut XL v9 | The flagship SDXL — 6M+ downloads |
| Juggernaut XL Lightning | v9-base speed variant |
| Juggernaut Z | Lumina-Image-2 — cinematic, presentation-ready |
| Juggernaut Pro Flux | FLUX.1 — top-tier photo quality |
License & Commercial Use
Juggernaut XI Lightning is released under CC BY-NC-ND 4.0:
- BY — attribute RunDiffusion / KandooAI when sharing output.
- NC — non-commercial use only. Commercial use requires a license.
- ND — no derivatives. You may not redistribute modified versions, fine-tunes, or merges.
This model may not be deployed behind paid API services or hosted on platforms that compete with RunDiffusion.com. For commercial licensing, contact juggernaut@rundiffusion.com.
Credits
Juggernaut XI Lightning was created by KandooAI in collaboration with RunDiffusion, distilled with SDXL Lightning. Photographic backbone by the RunDiffusion Photo team.
Ready to generate at speed?
Juggernaut XI Lightning — one click away on RunDiffusion. No gate, no setup.
Compare the full Juggernaut lineup · Prompting guides · Commercial licensing