SAVRN
Search Contact SAVRN

Open-weight model · Text to image

stable-diffusion-xl-base-1.0

by Stability AI stabilityai/stable-diffusion-xl-base-1.0

SDXL consists of an ensemble of experts pipeline for latent diffusion: In a first step, the base model is used to generate (noisy) latents, which are then further processed with a refinement model (available here…

Parameters2.6B
Context—
Weights63.8 GB
Licenseopenrail++
AccessOpen weights
Monthly Downloads2.9M

Runs On

What it takes to serve stable-diffusion-xl-base-1.0 (2.6B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso fits
16-bit 5.1 GB 6.2 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 2.6 GB 3.1 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 1.3 GB 1.5 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00

Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.

SAVRN's Notes on stable-diffusion-xl-base-1.0

The repository is 76.9 GB across 57 files; the run is 6.2 GB. One 16-bit copy of this 2.6B-parameter text-to-image model is 5.1 GB of weights, 4-bit needs 1.5 GB, and the page's 63.8 GB of weight files in safetensors and onnx hold far more than either, so pull only the format you serve. One MI300X at $1.85 an hour on-demand is the cheapest listing on our Index that fits, and this fills one thirtieth of its 192 GB.

Open RAIL++ permits commercial use but carries use-based restrictions that pass to your downstream users, so they belong in your own terms if you sell images; nothing is gated. Stability AI pairs this base with a separate refiner model for the final denoising steps and says the base runs standalone; decide which you are deploying, since the refiner is a second download and footprint. The files last moved 2023-10-30.

SAVRN Research, 2026-09-18

Model Card

By Stability AI, published under openrail++, revision 462165984030.

SD-XL 1.0-base Model Card

Model

SDXL consists of an ensemble of experts pipeline for latent diffusion: In a first step, the base model is used to generate (noisy) latents, which are then further processed with a refinement model (available here: https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0/) specialized for the final denoising steps. Note that the base model can be used as a standalone module.

Alternatively, we can use a two-stage pipeline as follows: First, the base model is used to generate latents of the desired output size. In the second step, we use a specialized high-resolution model and apply a technique called SDEdit (https://arxiv.org/abs/2108.01073, also known as "img2img") to the latents generated in the first step, using the same prompt. This technique is slightly slower than the first one, as it requires more function evaluations.

Source code is available at https://github.com/Stability-AI/generative-models .

Model Description

Read the full model card (961 words)

Identity and Version

Repository
stabilityai/stable-diffusion-xl-base-1.0
Publisher
Stability AI
Task
Text to image
Modality
Image
Library
diffusers
Parameters
2.6B parameters
Languages
Not stated by the source
Revision
462165984030d82259a11f4367a4eed129e94a7b
First published
2023-07-25
Last updated
2023-10-30

Files and Weights

57 files, 76.9 GB in total. The weights are 27 files totalling 63.8 GB in bin, msgpack, onnx, safetensors.

Weights27 files · 63.8 GB
Configuration11 files · 7.3 KB
Tokenizer6 files · 3.2 MB
Documentation2 files · 22.8 KB
Other10 files · 13.1 GB
Repository1 file · 1.6 KB
Every file
FileTypeSizeSHA-256
sd_xl_base_1.0.safetensorsWeights6.9 GB 31e35c80fc48
sd_xl_base_1.0_0.9vae.safetensorsWeights6.9 GB e6bb9ea85bbf
sd_xl_offset_example-lora_1.0.safetensorsWeights49.6 MB 4852686128f9
text_encoder/flax_model.msgpackWeights492.2 MB 80269e53c9d0
text_encoder/model.fp16.safetensorsWeights246.1 MB 660c6f5b1aba
text_encoder/model.onnxWeights492.6 MB e27bafa0b302
text_encoder/model.safetensorsWeights492.3 MB 5c3d6454dd2d
text_encoder/openvino_model.binWeights492.2 MB bbc78395c8ce
text_encoder_2/flax_model.msgpackWeights2.8 GB dc025fc8d206
text_encoder_2/model.fp16.safetensorsWeights1.4 GB ec310df2af79
text_encoder_2/model.onnxWeights1.0 MB 162042ac6556
text_encoder_2/model.safetensorsWeights2.8 GB 3a6032f63d37
text_encoder_2/openvino_model.binWeights2.8 GB 549d05154b0c
unet/diffusion_flax_model.msgpackWeights10.3 GB 0b98927b43cc
unet/diffusion_pytorch_model.fp16.safetensorsWeights5.1 GB 83e012a805b8
unet/diffusion_pytorch_model.safetensorsWeights10.3 GB 357650fbfb3c
unet/model.onnxWeights7.3 MB 6f001c090fb1
unet/openvino_model.binWeights10.3 GB 2d586bcb83c0
vae/diffusion_flax_model.msgpackWeights334.6 MB 1857495e1d4e
vae/diffusion_pytorch_model.fp16.safetensorsWeights167.3 MB bcb60880a46b
vae/diffusion_pytorch_model.safetensorsWeights334.6 MB 1598f3d24932
vae_1_0/diffusion_pytorch_model.fp16.safetensorsWeights167.3 MB eb6516ab7e11
vae_1_0/diffusion_pytorch_model.safetensorsWeights334.6 MB 27ed3b02e096
vae_decoder/model.onnxWeights198.1 MB 0892c5e28b35
vae_decoder/openvino_model.binWeights198.0 MB 34ea744ad1d7
vae_encoder/model.onnxWeights136.8 MB 7b117fbb2153
vae_encoder/openvino_model.binWeights136.7 MB 97f04b0cf748
model_index.jsonConfiguration609 B —
scheduler/scheduler_config.jsonConfiguration479 B —
text_encoder/config.jsonConfiguration565 B —
text_encoder_2/config.jsonConfiguration575 B —
tokenizer/special_tokens_map.jsonConfiguration472 B —
tokenizer_2/special_tokens_map.jsonConfiguration460 B —
unet/config.jsonConfiguration1.7 KB —
vae/config.jsonConfiguration642 B —
vae_1_0/config.jsonConfiguration607 B —
vae_decoder/config.jsonConfiguration607 B —
vae_encoder/config.jsonConfiguration607 B —
LICENSE.mdDocumentation14.1 KB —
README.mdDocumentation8.7 KB —
01.pngOther4.6 MB f40474e9ef87
comparison.pngOther130.3 KB —
pipeline.pngOther80.2 KB —
text_encoder/openvino_model.xmlOther1.1 MB ab5cf7327374
text_encoder_2/model.onnx_dataOther2.8 GB 3da7ac65349f
text_encoder_2/openvino_model.xmlOther2.8 MB 38f0a4ff68dd
unet/model.onnx_dataOther10.3 GB 7905b71f0044
unet/openvino_model.xmlOther22.6 MB 18955f96dffd
vae_decoder/openvino_model.xmlOther992.2 KB dd61f43e9812
vae_encoder/openvino_model.xmlOther850.0 KB a3ec36b6f3f7
.gitattributesRepository1.6 KB —
tokenizer/merges.txtTokenizer524.6 KB —
tokenizer/tokenizer_config.jsonTokenizer737 B —
tokenizer/vocab.jsonTokenizer1.1 MB —
tokenizer_2/merges.txtTokenizer524.6 KB —
tokenizer_2/tokenizer_config.jsonTokenizer725 B —
tokenizer_2/vocab.jsonTokenizer1.1 MB —

License and Download

License
openrail++
Access
Open weights, no gate
Download size
63.8 GB
Download from Stability AI

Released by Stability AI through its official repository on Hugging Face.

Built From

  • Described by arXiv:2108.01073
  • Described by arXiv:2112.10752
  • Described by arXiv:2211.01324
  • Described by arXiv:2307.01952

Memory Requirements

PrecisionWeights in memory
As published63.8 GB
16-bit5.1 GB
8-bit2.6 GB
4-bit1.3 GB

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

Built on This Model

Compare stable-diffusion-xl-base-1.0

Questions About stable-diffusion-xl-base-1.0

How much GPU memory does stable-diffusion-xl-base-1.0 need?

About 6.2 GB at 16-bit and 1.5 GB at 4-bit: the weights (2.6B parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run stable-diffusion-xl-base-1.0 on?

At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

Can I use stable-diffusion-xl-base-1.0 commercially?

Yes, with conditions. stable-diffusion-xl-base-1.0 is released under Open RAIL++ License. Open RAIL++ permits use, including commercial use, subject to the use-based restrictions listed in the license, which must be passed on to downstream users.

Similar Models

Model · Text to image

sdxl-turbo

Stability AI

SDXL-Turbo is a fast generative text-to-image model that can synthesize photorealistic images from a text prompt in a single network evaluation. A real-time demo is available here: http://clipdrop.co/stable-diffusion-turbo Please note: For commercial use, please refer to https://stability.ai/license. SDXL-Turbo is a distilled version of SDXL 1.0, trained for real-time synthesis. SDXL-Turbo is based on a novel training method called Adversarial Diffusion Distillation (ADD) (see the technical report), which allows sampling large-scale foundational image diffusion models in 1 to 4 steps at high image quality. This approach uses score distillation to leverage large-scale off-the-shelf image…

Open weights other 2.6B parameters diffusers
View model

Model · Text to image

animagine-xl-4.0

Cagliostro Labs

Animagine XL 4.0, also stylized as Anim4gine, is the ultimate anime-themed finetuned SDXL model and the latest installment of Animagine XL series. Despite being a continuation, the model was retrained from Stable Diffusion XL 1.0 with a massive dataset of 8.4M diverse anime-style images from various sources with the knowledge cut-off of January 7th 2025 and finetuned for approximately 2650 GPU hours. Similar to the previous version, this model was trained using tag ordering method for the identity and style training. With the release of Animagine XL 4.0 Opt (Optimized), the model has been further refined with an additional dataset, improving stability, anatomy accuracy, noise reduction…

Open weights openrail++ 2.6B parameters diffusers
View model

This repository contains a model that generates highly aesthetic images of resolution 1024x1024, as well as portrait and landscape aspect ratios. You can use the model with Hugging Face Diffusers. Playground v2.5 is a diffusion-based text-to-image generative model, and a successor to Playground v2. Playground v2.5 is the state-of-the-art open-source model in aesthetic quality. Our user studies demonstrate that our model outperforms SDXL, Playground v2, PixArt-α, DALL-E 3, and Midjourney 5.2. For details on the development and training of our model, please refer to our blog post and technical report. Install diffusers >= 0.27.0 and the relevant dependencies. - The pipeline uses the…

Open weights other 2.6B parameters diffusers
View model

Model · Text to image

animagine-xl-3.1

Cagliostro Labs

/ FIXED: Changed from 50% to 33.33% because there are 3 columns / margin-bottom: 1em; / Added small margin for spacing between stacked images / font-weight: bold; / Corrected 'font-style: bold' to 'font-weight: bold' / } / FIXED: Added missing closing brace here /.overlay, Animagine XL 3.1 is an update in the Animagine XL V3 series, enhancing the previous version, Animagine XL 3.0. This open-source, anime-themed text-to-image model has been improved for generating anime-style images with higher quality. It includes a broader range of characters from well-known anime series, an optimized dataset, and new aesthetic tags for better image creation. Built on Stable Diffusion XL, Animagine XL 3.1…

Open weights openrail++ 2.6B parameters diffusers
View model

Model · Text to image

noobai-XL-1.1

Laxhar Dream Lab

This is an image generation model based on training from Illustrious-xl. It utilizes the latest full Danbooru and e621 datasets for training, with native tags caption. For quality tags, we evaluated image popularity through the following process: - Data normalization based on various sources and ratings. - Application of time-based decay coefficients according to date recency. - Ranking of images within the entire dataset based on this processing. Our ultimate goal is to ensure that quality tags effectively track user preferences in recent years. - Latest Danbooru images up to the training date(for v1.0,it mean approximately before 2024-10-23) - E621 images e621-2024-webp-4Mpixel dataset on…

Open weights other 2.6B parameters diffusers
View model