Juggernaut XL v2 is one of the earliest Juggernaut SDXL checkpoints — the technically best of the first four versions. It predates the RunDiffusion Photo integration that defined v6 onward, so the photographic feel is rawer and more SDXL-base-like. Kept here for reference and for workflows that depend on it.
⚠️ For new projects, use the latest
Juggernaut has come a long way since v2. Two years of training, captioning, and photo-model improvements:
| Newer model | Why upgrade |
|---|---|
| Juggernaut XL v9 | The flagship SDXL — RunDiffusion Photo v2. 6M+ downloads. |
| Juggernaut X / XI | Ground-up retrains with GPT-4V captions |
| Juggernaut Z | Lumina-Image-2 architecture — cinematic out of the box |
| Juggernaut Pro Flux | FLUX.1 backbone — top-tier photo quality |
Recommended Settings
| Parameter | Value |
|---|---|
| Resolution | 832 × 1216 (portrait) · 1216 × 832 (landscape) |
| Sampler | DPM++ 2M Karras |
| Steps | 30 – 40 |
| CFG scale | 4 – 7 |
| VAE | Use the SDXL fp16-fix VAE for best results |
📖 Want to go deeper? See the RunDiffusion prompting library. Free to read.
Commercial Use
This model may not be deployed behind paid API services without explicit licensing. Contact juggernaut@rundiffusion.com for commercial licensing.
Personal/creative use under CreativeML Open RAIL-M.
Credits
Juggernaut XL v2 was created by KandooAI in collaboration with RunDiffusion.