import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("RunDiffusion/Juggernaut-X-v10", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]
Juggernaut X v10 by RunDiffusion
The ground-up retrain — GPT-4V captions, sharper prompt adherence, native text rendering.
Juggernaut X (v10) is a ground-up retrain of the Juggernaut SDXL line. Not a fine-tune of v9 — the entire dataset was re-captioned with GPT-4 Vision, image classifications were rebuilt from scratch, and the model was trained fresh against an expanded, higher-quality image set. The result: noticeably better prompt adherence, cleaner shot-type control, and native text-rendering capability.
What's Different in X / v10
- 🧠 Retrained from the ground up — not fine-tuned on top of a previous Juggernaut.
- 👁️ GPT-4 Vision captioning — dataset re-captioned with detailed, structured language descriptions.
- 🎯 Stronger prompt adherence — does what you ask more often, with less wrestling.
- 📸 Cleaner shot-type classification — Full Body, Mid Shot, Portrait, etc., now distinct in the model's understanding.
- 🔤 Native text rendering — handles legible signage, labels, and short phrases directly.
- 🖼️ RunDiffusion Photo refinement — same photographic backbone that made v9 popular.
🚀 Skip the setup. Try Juggernaut X in your browser.
No installs. No GPU rental. No model downloads. Just generate.
Pre-loaded into ComfyUI · Forge · Automatic1111 · Fooocus · InvokeAI · SwarmUI
Two Prompting Styles
X supports two distinct prompt styles. Pick whichever fits your workflow:
| Style | Best for | Example |
|---|---|---|
| Natural language | Storytelling, scenes, complex instructions | "A photographer on a windswept cliff at golden hour, holding a vintage Leica, the ocean churning below" |
| Tagging | Quick iteration, established workflows, LoRA stacking | photograph, photographer, cliff, golden hour, vintage Leica camera, ocean, waves, cinematic lighting |
📖 For deeper prompting technique — see the RunDiffusion prompting library. Free to read, no signup.
Two Ways to Run Juggernaut X
🚀 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
import torch
from diffusers import DiffusionPipeline
pipe = DiffusionPipeline.from_pretrained(
"RunDiffusion/Juggernaut-X-v10",
torch_dtype=torch.float16,
use_safetensors=True,
).to("cuda")
prompt = "A photographer on a windswept cliff at golden hour, holding a vintage Leica, the ocean churning below, cinematic lighting, hyperdetailed photography"
image = pipe(prompt, width=832, height=1216, num_inference_steps=35, guidance_scale=5.0).images[0]
image.save("juggernaut_x_v10.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 |
Two Versions: SAFE and Standard
Juggernaut X ships in two flavors:
- Juggernaut X (this repo) — the standard creative model.
- Juggernaut X SAFE — a safety-tuned variant for workplace, education, and family-friendly contexts. Available exclusively on RunDiffusion via Fooocus. SAFE = Suitable Ai For Everyone.
Looking For Something Different?
| Model | Why pick it |
|---|---|
| Juggernaut XL v9 | The most popular Juggernaut — proven SDXL photorealism workhorse. 6M+ downloads. |
| Juggernaut XI v11 | Continuation of the SDXL line, post-X refinement |
| Juggernaut Z | Lumina-Image-2 architecture — cinematic, presentation-ready |
| Juggernaut Pro Flux | FLUX.1 backbone — top-tier photo quality with strong consistency |
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 X (v10) was created by KandooAI in collaboration with RunDiffusion. Dataset re-captioned with the GPT-4 Vision Captioning tool by LEOSAM. Photographic backbone by the RunDiffusion Photo team.
Ready to generate?
Juggernaut X is one click away — no setup, no GPU rental, no model downloads.
Compare the full Juggernaut lineup · Prompting guides · Commercial licensing
- Downloads last month
- 20,204