RunDiffusion
/

Juggernaut-XL-v9

@@ -1,68 +1,142 @@
 ---
 language:
 - en
-license: creativeml-openrail-m
 library_name: diffusers
-tags:
-- art
-- people
-- diffusion
-- Cinematic
-- Photography
-- Landscape
-- Interior
-- Food
-- Car
-- Wildlife
-- Architecture
-thumbnail: >-
-  https://imagedelivery.net/siANnpeNAc_S2q1M3-eDrA/c200a026-c151-49c7-afbc-241fe943b300/padthumb
-base_model: stabilityai/stable-diffusion-xl-base-1.0
 pipeline_tag: text-to-image
 ---
-# Juggernaut XL v9 + RunDiffusion Photo v2 Official
-[![RunDiffusion Logo](https://imagedelivery.net/siANnpeNAc_S2q1M3-eDrA/ca2b388d-a835-490c-dec0-e764bee8d000/micro)](https://rundiffusion.com)
-Check out the team behind this amazing model! We're happy to help you build your Ai models!
-![juggernaut XL photo previews](https://imagedelivery.net/siANnpeNAc_S2q1M3-eDrA/c200a026-c151-49c7-afbc-241fe943b300/public)
-This model is not permitted to be used behind API services. Please contact [juggernaut@rundiffusion.com](mailto:juggernaut@rundiffusion.com) for business inquires, commercial licensing, custom models, and consultation.
-Juggernaut is available on the new Auto1111 Forge on [RunDiffusion](http://rundiffusion.com/?utm_source=huggingface&utm_medium=referral&utm_campaign=Kandoo)
-A big thanks for Version 9 goes to  [RunDiffusion](http://rundiffusion.com/?utm_source=huggingface&utm_medium=referral&utm_campaign=Kandoo)  ([Photo Model](https://rundiffusion.com/rundiffusion-photo/?utm_source=huggingface&utm_medium=referral&utm_campaign=Kandoo)) and  [Adam](https://twitter.com/Colorblind_Adam), who diligently helped me test :) (Leave some love for them ;) )
-It's time for another round, this time a bit delayed, but I hope you forgive the delay. Let's dive straight into the changes that await you or what we've been working on lately:
-For V9, I myself have only done basic training. This involves some work on skin details, lighting, and overall contrast. However, the biggest change to the model came from the [RunDiffusion Photo Model](https://rundiffusion.com/rundiffusion-photo/?utm_source=huggingface&utm_medium=referral&utm_campaign=Kandoo) update, which was made available to me in V2 by [RunDiffusion.com](https://rundiffusion.com/?utm_source=huggingface&utm_medium=referral&utm_campaign=Kandoo). The photographic output of the model should, in our experience, be even stronger than in previous versions.
-Now for a small "roadmap" update, or a general status update on how things are progressing with Juggernaut. As you may have noticed, there was a slight delay with V9. With each successive version, it has become increasingly difficult to train Juggernaut without sacrificing quality in some areas, which was already the case to some extent with V8. Don't worry, V9 is really good, and I'm satisfied with the version I can present to you today :) However, I've decided to go for a complete "reboot" for V10. I want to simply retrain the Juggernaut base set. The conditions for better captioning weren't as favorable "back then" as they are today, so I want to completely re-caption the base set (5k images) with GPT-4 Vision. I expect a big leap towards prompting guidance and quality.
-But as you surely noticed last week, the release of Stable Cascade got in the way a bit. Therefore, my focus in the coming weeks will be on training Juggernaut for Stable Cascade. The approach remains the same as with the planned "reboot"; I want to caption/tag all images in the future only with GPT-4 or manually. The timeline for all of this is still uncertain. I hope to be able to present you with a first stable version of Juggernaut Cascade sometime in March. V10 of Juggernaut XL will follow in the weeks thereafter.
-Now, here are some additional tips to make prompting easier for you:
- - Res: 832x1216
- - Sampler: DPM++ 2M Karras
- - Steps: 30-40 CFG: 3-7 (less is
-   a bit more realistic)
- - Negative: Start with no negative, and add afterwards the Stuff you don't want to see in that image. I don't recommend using my Negative Prompt, i simply use it because i am lazy  :D
-VAE is already Baked In
-HiRes: 4xNMKD-Siax_200k with 15 Steps and 0.3 Denoise + 1.5 Upscale
-And a few keywords/tokens that I regularly use in training, which might help you achieve the optimal result from the version:
- - 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
-![https://rundiffusion.com?utm_source=hf&utm_medium=referral&utm_campaign=juggernaut9](https://i.imgur.com/fKPEqSu.jpg)

 ---
+license: creativeml-openrail-m
 language:
 - en
 library_name: diffusers
 pipeline_tag: text-to-image
+base_model: stabilityai/stable-diffusion-xl-base-1.0
+tags:
+- stable-diffusion
+- stable-diffusion-xl
+- sdxl
+- text-to-image
+- photorealistic
+- photography
+- cinematic
+- portrait
+- juggernaut
+- rundiffusion
+- kandooai
 ---
+<div align="center">
+<a href="https://www.rundiffusion.com/juggernaut?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=header_banner">
+  <img src="https://huggingface.co/RunDiffusion/Juggernaut-XL-v9/resolve/main/assets/Juggernaut_v9_banner.png" alt="Juggernaut XL v9 — by RunDiffusion" />
+</a>
+<h1>Juggernaut XL v9 by RunDiffusion</h1>
+<p><i>The world's most-downloaded SDXL model — purpose-built for photorealism.</i></p>
+<p>
+  <a href="https://www.rundiffusion.com/juggernaut-xl?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=cta_primary"><img alt="Run Juggernaut XL on RunDiffusion" src="https://img.shields.io/badge/%E2%96%B6%20Run%20on%20RunDiffusion-7C3AED?style=for-the-badge&labelColor=7C3AED"></a>&nbsp;<a href="https://civitai.com/models/133005/juggernaut-xl"><img alt="Civitai" src="https://img.shields.io/badge/Civitai-Overwhelmingly%20Positive-1971c2?style=for-the-badge&labelColor=1f1f23"></a>&nbsp;<a href="https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0"><img alt="Base Model: SDXL 1.0" src="https://img.shields.io/badge/%F0%9F%A4%97%20Base%20Model-SDXL%201.0-FFD21E?style=for-the-badge&labelColor=1f1f23"></a>&nbsp;<img alt="License: CreativeML Open RAIL-M" src="https://img.shields.io/badge/License-OpenRAIL--M-2ea44f?style=for-the-badge">
+</p>
+</div>
+> 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**: 1.5M+ downloads on Civitai, 100K+ monthly downloads on Hugging Face, 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** — 17+ 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](#looking-for-something-newer). For SDXL photorealism, this is the king of the hill.
+## What V9 Brought Over V8
+- **RunDiffusion Photo v2** integration — a substantial upgrade in 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
+## 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 are tokens trained into the model that 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
+```
+## Quick Start (Diffusers)
+```python
+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, or SwarmUI: download `Juggernaut-XL_v9_RunDiffusionPhoto_v2.safetensors` and drop it into your `models/checkpoints/` (or equivalent) directory.
+## 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](https://huggingface.co/RunDiffusion/Juggernaut-Z-Image)** | Lumina-Image-2 | Cinematic, presentation-ready output with stronger lighting and atmosphere |
+| **[Juggernaut Pro Flux](https://www.rundiffusion.com/juggernaut-pro-flux?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=cross_promo_pro_flux)** | FLUX.1 | Highest photo quality with strong consistency and lower token cost |
+| **[Juggernaut XII / XIII Ragnarok](https://www.rundiffusion.com/juggernaut?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=cross_promo_family)** | 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 |
+## 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](mailto: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](https://huggingface.co/spaces/CompVis/stable-diffusion-license).
+## Credits
+Juggernaut XL v9 was created by **[KandooAI](https://twitter.com/Colorblind_Adam)** in collaboration with **[RunDiffusion](https://www.rundiffusion.com/?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=credits)**. The photographic backbone — **RunDiffusion Photo v2** — was developed by the RunDiffusion team. Thanks to **Adam Stewart** for helping shape the prompting workflow.
+## Links
+- 🚀 **Run it on RunDiffusion** → [rundiffusion.com/juggernaut-xl](https://www.rundiffusion.com/juggernaut-xl?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=footer_run)
+- 🧰 **Compare the full Juggernaut lineup** → [rundiffusion.com/juggernaut](https://www.rundiffusion.com/juggernaut?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=footer_lineup)
+- 🎨 **Civitai listing** → [civitai.com/models/133005](https://civitai.com/models/133005/juggernaut-xl)
+- 📐 **Base model** → [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)