---
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
- juggernaut
- rundiffusion
- kandooai
---
> Juggernaut XL v7 sits between [**v6**](https://huggingface.co/RunDiffusion/Juggernaut-XL-v6) and [**v8**](https://huggingface.co/RunDiffusion/Juggernaut-XL-v8) in the **RunDiffusion Photo v1** generation of the Juggernaut SDXL line. Released for users who needed a refresh between the major v6 and v8 milestones.
> **⚠️ FP16 users:** if you see black images or NaN errors in fp16 inference, use the [**v7-fp16-vae-fix variant**](https://huggingface.co/RunDiffusion/Juggernaut-XL-v7-fp16-vae-fix) instead.
## When to use v7
- 🔬 You have **LoRAs or pipelines specifically validated against v7**.
- 📚 You're auditing the Juggernaut release line for research.
For new projects, **start with the latest Juggernaut models** instead.
---
🚀 Don't pick a version. Try every Juggernaut on RunDiffusion.
v6, v7, v8, v9, X, XI, Z, and Pro Flux — all pre-loaded. No installs. No model downloads.
Pre-loaded into ComfyUI · Forge · Automatic1111 · Fooocus · InvokeAI · SwarmUI
---
## The Newer Juggernauts
| Model | Why upgrade |
| --- | --- |
| [**Juggernaut XL v9**](https://huggingface.co/RunDiffusion/Juggernaut-XL-v9) | Direct successor — RunDiffusion Photo v2. **6M+ downloads.** |
| [**Juggernaut X / XI**](https://huggingface.co/RunDiffusion/Juggernaut-XI-v11) | Ground-up retrains with GPT-4V captions |
| [**Juggernaut Z**](https://huggingface.co/RunDiffusion/Juggernaut-Z-Image) | Lumina-Image-2 architecture — cinematic, presentation-ready |
| [**Juggernaut Pro Flux**](https://www.rundiffusion.com/juggernaut-pro-flux?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v7&utm_content=cross_promo_pro_flux) | FLUX.1 backbone — top-tier photo quality |
## 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 |
📖 **Want to go deeper?** See the [**RunDiffusion prompting library**](https://www.rundiffusion.com/prompting?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v7&utm_content=prompting_inline). Free to read, no signup.
## Commercial Use
This model **may not be deployed behind paid API services** without explicit licensing. Contact **[juggernaut@rundiffusion.com](mailto:juggernaut@rundiffusion.com)** for commercial licensing.
Personal/creative use under [CreativeML Open RAIL-M](https://huggingface.co/spaces/CompVis/stable-diffusion-license).
## Credits
Juggernaut XL v7 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_v7&utm_content=credits)**. Photographic backbone: **RunDiffusion Photo v1**.
---