RunDiffusion commited on
Commit
ddeb7fd
Β·
verified Β·
1 Parent(s): 383fb0f

Marketing-driven redesign: 3-tier CTA flow (hero/midpage/footer) to app.rundiffusion.com/login, prompting library link, 'try free in browser' positioning, WebP banner

Browse files
Files changed (1) hide show
  1. README.md +79 -36
README.md CHANGED
@@ -22,64 +22,72 @@ tags:
22
  <div align="center">
23
 
24
  <a href="https://www.rundiffusion.com/juggernaut?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=header_banner">
25
- <img src="https://huggingface.co/RunDiffusion/Juggernaut-XL-v9/resolve/main/assets/Juggernaut_v9_banner.png" alt="Juggernaut XL v9 β€” by RunDiffusion" />
26
  </a>
27
 
28
  <h1>Juggernaut XL v9 by RunDiffusion</h1>
29
 
30
  <p><i>The world's most-downloaded SDXL model β€” purpose-built for photorealism.</i></p>
31
 
 
 
32
  <p>
33
- <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">
 
 
 
 
34
  </p>
35
 
36
  </div>
37
 
38
- > Juggernaut XL is the most popular SDXL fine-tune in the world. Version 9 β€” co-developed by **KandooAI** and **RunDiffusion**, integrating **RunDiffusion Photo v2** β€” 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.
39
 
40
  ## Why Juggernaut XL v9 in 2026?
41
 
42
  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:
43
 
44
- - **Photorealism that holds up under scrutiny** β€” skin texture, micro-contrast, and natural lighting that translates from concept to print.
45
- - **Reasonable hardware** β€” runs comfortably on 8 GB of VRAM, unlike newer DiT-based models that demand 16+ GB.
46
- - **The full SDXL toolbox** β€” drop-in compatibility with the thousands of SDXL ControlNets, IP-Adapter variants, AnimateDiff, regional prompting tools, and LoRAs already in your workflow.
47
- - **Battle-tested reliability** β€” 17+ months in production, used in agencies, studios, and shipping products around the world.
48
 
49
  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.
50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
  ## What V9 Brought Over V8
52
 
53
- - **RunDiffusion Photo v2** integration β€” a substantial upgrade in the photographic backbone of the model
54
  - Improved **skin detail** and micro-texture rendering
55
  - Stronger **lighting** and **contrast** control
56
  - Better consistency across **portrait**, **architecture**, **automotive**, **wildlife**, **food**, **interior**, and **landscape** photography
57
 
58
- ## Recommended Settings
59
-
60
- | Parameter | Value |
61
- | --- | --- |
62
- | Resolution | `832 Γ— 1216` (portrait) Β· `1216 Γ— 832` (landscape) |
63
- | Sampler | `DPM++ 2M Karras` |
64
- | Steps | `30 – 40` |
65
- | CFG scale | `3 – 7` (lower = more realistic) |
66
- | VAE | **Already baked in** β€” no external VAE required |
67
- | Hi-Res fix | `4xNMKD-Siax_200k` upscaler Β· 15 steps Β· 0.3 denoise Β· 1.5Γ— upscale |
68
 
69
- > **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.
70
-
71
- ## Useful Prompt Keywords
72
 
73
- These are tokens trained into the model that reliably steer output:
74
 
75
- ```
76
- Architecture Photography Β· Wildlife Photography Β· Car Photography
77
- Food Photography Β· Interior Photography Β· Landscape Photography
78
- Hyperdetailed Photography Β· Cinematic Movie Β· Still Mid Shot Photo
79
- Full Body Photo Β· Skin Details
80
- ```
81
 
82
- ## Quick Start (Diffusers)
83
 
84
  ```python
85
  import torch
@@ -104,7 +112,33 @@ image = pipe(
104
  image.save("juggernaut_xl_v9.png")
105
  ```
106
 
107
- For ComfyUI, Forge, InvokeAI, or SwarmUI: download `Juggernaut-XL_v9_RunDiffusionPhoto_v2.safetensors` and drop it into your `models/checkpoints/` (or equivalent) directory.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
108
 
109
  ## Files In This Repo
110
 
@@ -124,6 +158,8 @@ The Juggernaut family has continued to evolve. Match the model to your project:
124
  | **[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 |
125
  | **Juggernaut XL v9** *(this model)* | SDXL 1.0 | Proven SDXL photorealism workhorse with the broadest tooling ecosystem |
126
 
 
 
127
  ## Commercial Use
128
 
129
  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)**.
@@ -132,11 +168,18 @@ You are free to use this model for personal and creative work under the terms of
132
 
133
  ## Credits
134
 
135
- 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 β€” **RunDiffusion Photo v2** β€” was developed by the RunDiffusion team. Thanks to **Adam Stewart** for helping shape the prompting workflow.
136
 
137
- ## Links
 
 
 
 
138
 
139
- - πŸš€ **Run it on RunDiffusion** β†’ [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)
140
- - 🧰 **Compare the full Juggernaut lineup** β†’ [rundiffusion.com/juggernaut](https://www.rundiffusion.com/juggernaut?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=footer_lineup)
141
- - 🎨 **Civitai listing** β†’ [civitai.com/models/133005](https://civitai.com/models/133005/juggernaut-xl)
142
- - πŸ“ **Base model** β†’ [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)
 
 
 
 
22
  <div align="center">
23
 
24
  <a href="https://www.rundiffusion.com/juggernaut?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=header_banner">
25
+ <img src="https://huggingface.co/RunDiffusion/Juggernaut-XL-v9/resolve/main/assets/Juggernaut_v9_banner.webp" alt="Juggernaut XL v9 β€” by RunDiffusion" />
26
  </a>
27
 
28
  <h1>Juggernaut XL v9 by RunDiffusion</h1>
29
 
30
  <p><i>The world's most-downloaded SDXL model β€” purpose-built for photorealism.</i></p>
31
 
32
+ <p><b>6M+ downloads on Hugging Face Β· Overwhelmingly Positive on Civitai Β· 26 months in production</b></p>
33
+
34
  <p>
35
+ <a href="https://app.rundiffusion.com/login?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=hero_cta"><img alt="Try Juggernaut XL v9 β€” Free" src="https://img.shields.io/badge/%E2%96%B6%20Try%20Juggernaut%20XL%20v9%20%E2%80%94%20Free-7C3AED?style=for-the-badge&labelColor=7C3AED"></a>
36
+ </p>
37
+
38
+ <p>
39
+ <a href="https://www.rundiffusion.com/prompting?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=prompting_resource"><img alt="Prompting Guides" src="https://img.shields.io/badge/%F0%9F%93%96%20Prompting%20Guides-1f1f23?style=for-the-badge"></a>&nbsp;<a href="https://www.rundiffusion.com/juggernaut?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=lineup_compare"><img alt="Compare the Lineup" src="https://img.shields.io/badge/Compare%20the%20Lineup-1971c2?style=for-the-badge&labelColor=1f1f23"></a>&nbsp;<a href="https://civitai.com/models/133005/juggernaut-xl"><img alt="Civitai" src="https://img.shields.io/badge/Civitai-Overwhelmingly%20Positive-EAB308?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">
40
  </p>
41
 
42
  </div>
43
 
44
+ > Juggernaut XL is the most popular SDXL fine-tune in the world. Version 9 β€” co-developed by **KandooAI** and **RunDiffusion**, integrating **RunDiffusion Photo v2** β€” 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.
45
 
46
  ## Why Juggernaut XL v9 in 2026?
47
 
48
  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:
49
 
50
+ - πŸ“Έ **Photorealism that holds up under scrutiny** β€” skin texture, micro-contrast, and natural lighting that translates from concept to print.
51
+ - πŸ’» **Reasonable hardware** β€” runs comfortably on 8 GB of VRAM, unlike newer DiT-based models that demand 16+ GB.
52
+ - 🧰 **The full SDXL toolbox** β€” drop-in compatibility with the thousands of SDXL ControlNets, IP-Adapter variants, AnimateDiff, regional prompting tools, and LoRAs already in your workflow.
53
+ - πŸ† **Battle-tested reliability** β€” 26+ months in production, used in agencies, studios, and shipping products around the world.
54
 
55
  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.
56
 
57
+ ---
58
+
59
+ <div align="center">
60
+
61
+ ### πŸš€ Skip the setup. Try Juggernaut XL v9 in your browser.
62
+
63
+ No installs. No GPU rental. No model downloads. **Just generate.**
64
+
65
+ <a href="https://app.rundiffusion.com/login?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=midpage_cta"><img alt="Launch Juggernaut on RunDiffusion" src="https://img.shields.io/badge/%E2%96%B6%20Launch%20on%20RunDiffusion-7C3AED?style=for-the-badge&labelColor=7C3AED"></a>
66
+
67
+ *Pre-loaded into ComfyUI Β· Forge Β· Automatic1111 Β· Fooocus Β· InvokeAI Β· SwarmUI*
68
+
69
+ </div>
70
+
71
+ ---
72
+
73
  ## What V9 Brought Over V8
74
 
75
+ - **RunDiffusion Photo v2** integration β€” a substantial upgrade to the photographic backbone of the model
76
  - Improved **skin detail** and micro-texture rendering
77
  - Stronger **lighting** and **contrast** control
78
  - Better consistency across **portrait**, **architecture**, **automotive**, **wildlife**, **food**, **interior**, and **landscape** photography
79
 
80
+ ## Two Ways to Run Juggernaut XL v9
 
 
 
 
 
 
 
 
 
81
 
82
+ ### πŸš€ Easiest β€” Run it on RunDiffusion (recommended)
 
 
83
 
84
+ One-click access to Juggernaut XL v9 inside the UI you already know β€” ComfyUI, Forge, Automatic1111, Fooocus, InvokeAI, or SwarmUI. No setup, no model downloads, no GPU to rent. **Free trial included.**
85
 
86
+ <div align="center">
87
+ <a href="https://app.rundiffusion.com/login?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=quickstart_try"><img alt="Get Started Free" src="https://img.shields.io/badge/Get%20Started%20Free%20%E2%86%92-7C3AED?style=for-the-badge&labelColor=7C3AED"></a>
88
+ </div>
 
 
 
89
 
90
+ ### πŸ’» Or run it locally β€” Diffusers
91
 
92
  ```python
93
  import torch
 
112
  image.save("juggernaut_xl_v9.png")
113
  ```
114
 
115
+ For ComfyUI / Forge / InvokeAI / SwarmUI: download `Juggernaut-XL_v9_RunDiffusionPhoto_v2.safetensors` and drop it into your `models/checkpoints/` directory.
116
+
117
+ ## Recommended Settings
118
+
119
+ | Parameter | Value |
120
+ | --- | --- |
121
+ | Resolution | `832 Γ— 1216` (portrait) Β· `1216 Γ— 832` (landscape) |
122
+ | Sampler | `DPM++ 2M Karras` |
123
+ | Steps | `30 – 40` |
124
+ | CFG scale | `3 – 7` (lower = more realistic) |
125
+ | VAE | **Already baked in** β€” no external VAE required |
126
+ | Hi-Res fix | `4xNMKD-Siax_200k` upscaler Β· 15 steps Β· 0.3 denoise Β· 1.5Γ— upscale |
127
+
128
+ > **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.
129
+
130
+ ### Useful Prompt Keywords
131
+
132
+ These tokens reliably steer output:
133
+
134
+ ```
135
+ Architecture Photography Β· Wildlife Photography Β· Car Photography
136
+ Food Photography Β· Interior Photography Β· Landscape Photography
137
+ Hyperdetailed Photography Β· Cinematic Movie Β· Still Mid Shot Photo
138
+ Full Body Photo Β· Skin Details
139
+ ```
140
+
141
+ πŸ“– **For deeper prompting technique** β€” sampler choices, multi-subject framing, lighting language, negative-prompt strategy β€” see the [**RunDiffusion prompting library**](https://www.rundiffusion.com/prompting?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=prompting_inline). Free to read, no signup.
142
 
143
  ## Files In This Repo
144
 
 
158
  | **[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 |
159
  | **Juggernaut XL v9** *(this model)* | SDXL 1.0 | Proven SDXL photorealism workhorse with the broadest tooling ecosystem |
160
 
161
+ All of them β€” and 100+ other SOTA models β€” are pre-loaded on **[RunDiffusion](https://app.rundiffusion.com/login?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=family_compare)**. Switch between them in two clicks.
162
+
163
  ## Commercial Use
164
 
165
  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)**.
 
168
 
169
  ## Credits
170
 
171
+ Juggernaut XL v9 was created by **[KandooAI](https://twitter.com/Juggernaut_AI)** 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 β€” **RunDiffusion Photo v2** β€” was developed by the RunDiffusion team. Thanks to **Adam Stewart** for prompting workflow.
172
 
173
+ ---
174
+
175
+ <div align="center">
176
+
177
+ ### Ready to generate?
178
 
179
+ Juggernaut XL v9 is one click away β€” no setup, no GPU rental, no model downloads.
180
+
181
+ <a href="https://app.rundiffusion.com/login?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=footer_cta"><img alt="Try Juggernaut XL v9 β€” Free" src="https://img.shields.io/badge/%E2%96%B6%20Try%20Juggernaut%20XL%20v9%20%E2%80%94%20Free-7C3AED?style=for-the-badge&labelColor=7C3AED"></a>
182
+
183
+ <sub><a href="https://www.rundiffusion.com/juggernaut?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=footer_lineup">Compare the full Juggernaut lineup</a> Β· <a href="https://www.rundiffusion.com/prompting?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=footer_prompting">Prompting guides</a> Β· <a href="mailto:juggernaut@rundiffusion.com">Commercial licensing</a></sub>
184
+
185
+ </div>