Juggernaut XL v9 by RunDiffusion

The world's most-downloaded SDXL model — purpose-built for photorealism.

6M+ downloads on Hugging Face · Overwhelmingly Positive on Civitai · 26 months in production

Juggernaut XL is the most popular SDXL fine-tune in the world. Version 9 — co-developed by KandooAI and RunDiffusion, integrating RunDiffusion Photo v2 — is the proven photorealism workhorse trusted by hundreds of thousands of creators: 6M+ all-time downloads on Hugging Face, 1.5M+ on Civitai, and an Overwhelmingly Positive rating across 7,780+ reviews.

Why Juggernaut XL v9 in 2026?

The SDXL ecosystem is the single most mature corner of open image generation, and v9 is its most refined photorealism checkpoint. Choose Juggernaut XL v9 when you want:

📸 Photorealism that holds up under scrutiny — skin texture, micro-contrast, and natural lighting that translates from concept to print.
💻 Reasonable hardware — runs comfortably on 8 GB of VRAM, unlike newer DiT-based models that demand 16+ GB.
🧰 The full SDXL toolbox — drop-in compatibility with the thousands of SDXL ControlNets, IP-Adapter variants, AnimateDiff, regional prompting tools, and LoRAs already in your workflow.
🏆 Battle-tested reliability — 26+ months in production, used in agencies, studios, and shipping products around the world.

For experimental and frontier work, see the rest of the Juggernaut family. For SDXL photorealism, this is the king of the hill.

🚀 Skip the setup. Try Juggernaut XL v9 in your browser.

No installs. No GPU rental. No model downloads. Just generate.

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

What V9 Brought Over V8

RunDiffusion Photo v2 integration — a substantial upgrade to the photographic backbone of the model
Improved skin detail and micro-texture rendering
Stronger lighting and contrast control
Better consistency across portrait, architecture, automotive, wildlife, food, interior, and landscape photography

Two Ways to Run Juggernaut XL v9

🚀 Easiest — Run it on RunDiffusion (recommended)

One-click access to Juggernaut XL v9 inside the UI you already know — ComfyUI, Forge, Automatic1111, Fooocus, InvokeAI, or SwarmUI. No setup, no model downloads, no GPU to rent. Free trial included.

💻 Or run it locally — Diffusers

import torch
from diffusers import DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained(
    "RunDiffusion/Juggernaut-XL-v9",
    torch_dtype=torch.float16,
    variant="fp16",
    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_v9.png")

For ComfyUI / Forge / InvokeAI / SwarmUI: download Juggernaut-XL_v9_RunDiffusionPhoto_v2.safetensors 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. Heavy negatives often hurt more than they help on this model.

Useful Prompt Keywords

These tokens reliably steer output:

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

📖 For deeper prompting technique — sampler choices, multi-subject framing, lighting language, negative-prompt strategy — see the RunDiffusion prompting library. Free to read, no signup.

Files In This Repo

File	Purpose
`Juggernaut-XL_v9_RunDiffusionPhoto_v2.safetensors`	Single-file checkpoint for ComfyUI / Forge / InvokeAI / SwarmUI
`unet/`, `text_encoder/`, `text_encoder_2/`, `vae/`, `tokenizer/`, `tokenizer_2/`, `scheduler/`, `model_index.json`	Diffusers-format directory tree (FP16 variant) for `from_pretrained`

Looking For Something Newer?

The Juggernaut family has continued to evolve. Match the model to your project:

Model	Architecture	Best for
Juggernaut Z	Lumina-Image-2	Cinematic, presentation-ready output with stronger lighting and atmosphere
Juggernaut Pro Flux	FLUX.1	Highest photo quality with strong consistency and lower token cost
Juggernaut XII / XIII Ragnarok	SDXL	The latest evolutions of the SDXL line, refined for prompt adherence and realism
Juggernaut XL v9 (this model)	SDXL 1.0	Proven SDXL photorealism workhorse with the broadest tooling ecosystem

All of them — and 100+ other SOTA models — are pre-loaded on RunDiffusion. Switch between them in two clicks.

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 v9 was created by KandooAI in collaboration with RunDiffusion. The photographic backbone — RunDiffusion Photo v2 — was developed by the RunDiffusion team. Thanks to Adam Stewart for prompting workflow.