SAVRN
Search Contact SAVRN

Open-weight model · Text to image

Juggernaut-XL-v9

by RunDiffusion RunDiffusion/Juggernaut-XL-v9

Juggernaut-XL-v9 is an open-weight model for text to image from RunDiffusion, released under CreativeML Open RAIL-M. Its published files total 14.0 GB. It draws 870.1k downloads a month.

The SDXL ecosystem is the single most mature corner of open image generation, and v9 is its most refined photorealism checkpoint.

Parameters—
Context—
Weights14.0 GB
Licensecreativeml-openrail-m
AccessOpen weights
Monthly Downloads870.1k

SAVRN's Notes on Juggernaut-XL-v9

The page states no parameter count, but the files tell the story: a single 7.1 GB safetensors checkpoint plus fp16 shards for the UNet (5.1 GB), both text encoders (246.1 MB and 1.4 GB) and the VAE (167.3 MB), 14.0 GB in all. This is an SDXL-class image model, derived from stabilityai/stable-diffusion-xl-base-1.0, and the 7.1 GB single file is the fp16 artifact you would actually load — there is no Runs On table here to price it, so budget a card that holds that file plus activations.

CreativeML Open RAIL-M permits commercial use but carries use-based restrictions that pass through to downstream users, so read the attachment before productizing. The card claims the most-downloaded SDXL fine-tune with 6M+ lifetime downloads; the Index shows 870.1k a month, still a large number. At 26 months in production it is a proven photorealism workhorse — but it is still SDXL, and neighbors like the FLUX family will beat it on prompt fidelity per GB.

SAVRN Research

Model Card

By RunDiffusion, published under creativeml-openrail-m, revision cf419233522d.

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:

Read the full model card (817 words)

Identity and Version

Repository
RunDiffusion/Juggernaut-XL-v9
Publisher
RunDiffusion
Task
Text to image
Modality
Image
Library
diffusers
Parameters
Not stated by the source
Languages
en
Revision
cf419233522daa0b9ea36c3aff98fa2cab1fb0fb
First published
2024-02-18
Last updated
2026-05-08

Files and Weights

23 files, 14.0 GB in total. The weights are 5 files totalling 14.0 GB in safetensors.

Weights5 files · 14.0 GB
Configuration8 files · 5.7 KB
Tokenizer6 files · 3.2 MB
Documentation1 file · 10.5 KB
Other2 files · 2.9 MB
Repository1 file · 1.7 KB
Every file
FileTypeSizeSHA-256
Juggernaut-XL_v9_RunDiffusionPhoto_v2.safetensorsWeights7.1 GB c9e3e68f89b8
text_encoder/model.fp16.safetensorsWeights246.1 MB 698656aa4f45
text_encoder_2/model.fp16.safetensorsWeights1.4 GB 9962c194f50a
unet/diffusion_pytorch_model.fp16.safetensorsWeights5.1 GB cf1ee18eb367
vae/diffusion_pytorch_model.fp16.safetensorsWeights167.3 MB 6353737672c9
model_index.jsonConfiguration667 B —
scheduler/scheduler_config.jsonConfiguration496 B —
text_encoder/config.jsonConfiguration565 B —
text_encoder_2/config.jsonConfiguration575 B —
tokenizer/special_tokens_map.jsonConfiguration588 B —
tokenizer_2/special_tokens_map.jsonConfiguration462 B —
unet/config.jsonConfiguration1.8 KB —
vae/config.jsonConfiguration607 B —
README.mdDocumentation10.5 KB —
assets/Juggernaut_v9_banner.pngOther2.6 MB 2b6cf4ee44e4
assets/Juggernaut_v9_banner.webpOther379.2 KB 82652584d311
.gitattributesRepository1.7 KB —
tokenizer/merges.txtTokenizer524.6 KB —
tokenizer/tokenizer_config.jsonTokenizer705 B —
tokenizer/vocab.jsonTokenizer1.1 MB —
tokenizer_2/merges.txtTokenizer524.6 KB —
tokenizer_2/tokenizer_config.jsonTokenizer856 B —
tokenizer_2/vocab.jsonTokenizer1.1 MB —

License and Download

License
creativeml-openrail-m
Access
Open weights, no gate
Download size
14.0 GB
Download from RunDiffusion

Released by RunDiffusion through its official repository on Hugging Face.

Built From

Memory Requirements

PrecisionWeights in memory
As published14.0 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About Juggernaut-XL-v9

Can I use Juggernaut-XL-v9 commercially?

Yes, with conditions. Juggernaut-XL-v9 is released under CreativeML Open RAIL-M. CreativeML Open RAIL-M permits use, including commercial use, subject to the use-based restrictions in its attachment, which must be passed on downstream.

Similar Models

GGUF quantizations of Qwen/Qwen-Image-2.1 for local image generation using the original upstream base weights. Q4KM is recommended for the best balance of size and quality. Companion model files packaged for ComfyUI: Use the model with ComfyUI and ComfyUI-GGUF. All required companion files (GGUF transformer, text encoder, and VAE) are hosted directly in this repository. Download the files and place them in their respective ComfyUI directories: 1. Install ComfyUI-GGUF: Use the maintained fork with native Qwen-Image 2.1 support by cloning leejet/ComfyUI-GGUF into your custom nodes: (Note: If you have the older city96/ComfyUI-GGUF installed and encounter an Unknown model architecture! error…

Open weights other gguf
View model

GGUF, Safetensors, and MLX quantized formats of Qwen/Qwen-Image-2.1 for local image generation using the original upstream base weights. Q4KM is recommended for the best balance of size and quality for GGUF. INT8 ConvRot and NVFP4 offer high performance on supported GPUs, while MLX formats are optimized for Apple Silicon. Companion model files packaged for ComfyUI: Use the model with ComfyUI and ComfyUI-GGUF. All required companion files (GGUF transformer, text encoder, and VAE) are hosted directly in this repository. Download the files and place them in their respective ComfyUI directories: 1. Install ComfyUI-GGUF: Use the maintained fork with native Qwen-Image 2.1 support by cloning…

Open weights other gguf
View model

Model · Text to image

Z-Image-Turbo-GGUF

Unsloth AI

Welcome to the official repository for the Z-Image（造相）project! Z-Image is a powerful and highly efficient image generation model with 6B parameters. Currently there are three variants: - Z-Image-Turbo – A distilled version of Z-Image that matches or exceeds leading competitors with only 8 NFEs (Number of Function Evaluations). It offers sub-second inference latency on enterprise-grade H800 GPUs and fits comfortably within 16G VRAM consumer devices. It excels in photorealistic image generation, bilingual text rendering (English & Chinese), and robust instruction adherence. - Z-Image-Base – The non-distilled foundation model. By releasing this checkpoint, we aim to unlock the full potential…

Open weights apache-2.0 ggml
View model

Model · Text to image

Qwen-Image-2.1-GGUF

Unsloth AI

This is a GGUF quantized version of Qwen-Image-2.1. unsloth/Qwen-Image-2.1-GGUF uses Unsloth Dynamic 2.0 methodology for SOTA performance. - Important layers are upcasted to higher precision, per tensor, from a measured sensitivity scan. - Run these with Unsloth Desktop, stable-diffusion.cpp and more. A GGUF is the denoiser only, so it needs the VAE and the Qwen3-VL text encoder alongside it. See below for image editing operating inside of Unsloth Desktop: Rendered with the Q4KM denoiser and the Q4KM text encoder, 1024x1024, 20 steps, cfg 6.0, euler. We are excited to open-source Qwen-Image-2.1, a unified text-to-image generation and image editing model in the Qwen family. With just 7B…

Open weights other
View model

Model · Text to image

Qwen-Image-Lightning

Lightx2v

Please refer to Qwen-Image-Lightning github to learn how to use the models. make sure to install diffusers from main (pip install git+https://github.com/huggingface/diffusers.git)

Open weights apache-2.0 diffusers
View model

Model · Text to image

Z-Image-Lora

nphSi

+ Always use full LoRa name with "vrtlxxxx" trigger in prompt like "Alba Baptista (vrtlalbabaptista) in a swimming pool". "Woman" or "1girl" will NOT work due to my way i do captions. + Add the gender to the prompt for confusing names like "Alex Jones". + Remove the name when internal model knowledge is bad or censored or is confusing to model like "Sandy Cheeks" or "Kate Middleton". + When using a Lora with multiple triggers (vrtlxx,vrtlyy) do not use the real character name but only trigger or a combination of it. "vrtlMain" always combines all trigger-words. Angourie Rice, January Jones, Julianna Guill, Ursula Corbero, Judith Rakers, Alina Merkau, Kiernan Shipka, Leslie Bibb, Marie…

Open weights apache-2.0 diffusers
View model