RunDiffusion/Juggernaut-XL-v6

Juggernaut XL v6 by RunDiffusion

The original RunDiffusion Photo-fused SDXL release — over 3 million downloads strong.

   

Juggernaut XL v6 is the original photo-fused SDXL release in the Juggernaut line — the version that introduced RunDiffusion Photo v1 to the Juggernaut family and turned it into the most-downloaded SDXL fine-tune in the world. Two years on, 3M+ downloads and counting.

When to use v6

V6 still serves a real audience. Choose it when you:

• 🔬 Have LoRAs, ControlNets, embeddings, or pipelines trained or tuned against v6 and want bit-for-bit consistency.
• 🏭 Run an automated production pipeline that has been validated against v6 and you don't want to revalidate against a newer checkpoint.
• 🎨 Need the exact v6 aesthetic — slightly softer lighting and more muted contrast than the later versions.

For new projects, start with the latest Juggernaut models instead — they apply two years of additional training, captioning, and photo-model improvements.

---

🚀 Don't pick a version. Try every Juggernaut on RunDiffusion.

v6, v9, X, XI, Z, and Pro Flux — all pre-loaded. Switch in two clicks. No installs. No model downloads.

Pre-loaded into ComfyUI · Forge · Automatic1111 · Fooocus · InvokeAI · SwarmUI

---

The Newer Juggernauts

Model	Why upgrade
Juggernaut XL v9	Direct successor on SDXL — RunDiffusion Photo v2, sharper skin, stronger lighting. 6M+ downloads.
Juggernaut XI / X	Ground-up retrains with GPT-4V captions — better prompt adherence
Juggernaut Z	Lumina-Image-2 architecture — cinematic, presentation-ready
Juggernaut Pro Flux	FLUX.1 backbone — top-tier photo quality with strong consistency

Two Ways to Run Juggernaut XL v6

🚀 Easiest — Run it on RunDiffusion (recommended)

One-click access inside the UI you already know — 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

import torch
from diffusers import DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained(
    "RunDiffusion/Juggernaut-XL-v6",
    torch_dtype=torch.float16,
    use_safetensors=True,
).to("cuda")

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=832, height=1216,
    num_inference_steps=35,
    guidance_scale=5.0,
).images[0]

image.save("juggernaut_xl_v6.png")

For ComfyUI / Forge / InvokeAI / SwarmUI: download the single-file checkpoint and drop it into your models/checkpoints/ directory.

Recommended Settings

Parameter	Value
Resolution	832 × 1216 (portrait) · 1216 × 832 (landscape)
Sampler	DPM++ 2M Karras
Steps	30 – 40
CFG scale	3 – 7 (lower = more realistic)
VAE	Already baked in — no external VAE required
Hi-Res fix	4xNMKD-Siax_200k upscaler · 15 steps · 0.3 denoise · 1.5× upscale

Negative prompts: start with none. Add specific things you don't want as you iterate.

Useful Prompt Keywords

Architecture Photography · Wildlife Photography · Car Photography
Food Photography · Interior Photography · Landscape Photography
Hyperdetailed Photography · Cinematic Movie · Still Mid Shot Photo
Full Body Photo · Skin Details

📖 Want to go deeper? Sampler choices, multi-subject framing, lighting language, negative-prompt strategy — see the RunDiffusion prompting library. Free to read, no signup.

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.

You are free to use this model for personal and creative work under the terms of the CreativeML Open RAIL-M license.

Credits

Juggernaut XL v6 was created by KandooAI in collaboration with RunDiffusion. Photographic backbone: RunDiffusion Photo v1.

---

Ready to generate?

v6, v9, and every other Juggernaut — one click away on RunDiffusion.

_{Compare the full Juggernaut lineup · Prompting guides · Commercial licensing}