# Illustrious-xl-early-release-v0 by OnomaAI: Open Model Source: https://savrn.com/models/illustrious-xl-early-release-v0 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve Illustrious-xl-early-release-v0 (2.6B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 5.1 GB | 6.2 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 2.6 GB | 3.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 1.3 GB | 1.5 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/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](https://savrn.com/ai-index/pricing/gpus), read Oct 25, 2026. [Illustrious-xl-early-release-v0 on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/illustrious-xl-early-release-v0/gpus) ## SAVRN's Notes on Illustrious-xl-early-release-v0 Illustrious XL is an illustration-focused SDXL model continued from Kohaku XL Beta 5, and this early release became a popular base for anime and illustration fine-tunes. It has 2.6B parameters and fits on a single consumer GPU. The license is listed as other, so read OnomaAI's terms and the terms of the models it builds on before commercial use. The repository is large at about 35 GB because it holds several formats; download only the one your pipeline loads. SAVRN Research, 2026-09-18 ## Model Card / Title Base Styling / rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.8.2/css/all.min.css" Illustrious XL is the Illustration focused Stable Diffusion XL model which is continued from Kohaku XL Beta 5, trained by OnomaAI Research Team. The model focuses on utilizing large-scale annotated dataset, Danbooru2023. We release the v0.1 and v0.1-GUIDED model here, under fair public ai license, however discourages the usage of model over monetization purpose / any closed source purposes. For full technical details, please refer to our technical report. We plan to release several aesthetic-finetuned model variants in near future. By using this model, users agree to… Excerpt from the card by OnomaAI, licensed other. ## Identity and Version Repository OnomaAIResearch/Illustrious-xl-early-release-v0 Publisher OnomaAI Task Text to image Modality Image Library diffusers Parameters 2.6B parameters Languages en Revision dca0dac303e6dc4b0c31d8001bc685b89b5d0204 First published 2024-09-20 Last updated 2025-02-13 ## Files and Weights 29 files, 34.9 GB in total. The weights are 10 files totalling 34.7 GB in bin, safetensors. Weights10 files · 34.7 GB Configuration8 files · 5.9 KB Tokenizer6 files · 3.2 MB Documentation1 file · 16.9 KB Other3 files · 236.3 MB Repository1 file · 1.7 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | Illustrious-XL-v0.1-GUIDED.safetensors | Weights | 6.9 GB | e3d12d0f76d6 | | Illustrious-XL-v0.1.safetensors | Weights | 6.9 GB | 3e15ba00387d | | text_encoder/model.safetensors | Weights | 246.1 MB | f8480c7d1b3e | | text_encoder/pytorch_model.bin | Weights | 492.3 MB | 5d26ce4bc994 | | text_encoder_2/model.safetensors | Weights | 1.4 GB | b3869d29e594 | | text_encoder_2/pytorch_model.bin | Weights | 2.8 GB | 9a87779e938a | | unet/diffusion_pytorch_model.bin | Weights | 10.3 GB | bb4545d21e40 | | unet/diffusion_pytorch_model.safetensors | Weights | 5.1 GB | 29c786282e39 | | vae/diffusion_pytorch_model.bin | Weights | 334.7 MB | 8848a782919b | | vae/diffusion_pytorch_model.safetensors | Weights | 167.3 MB | 6353737672c9 | | model_index.json | Configuration | 671 B | — | | scheduler/scheduler_config.json | Configuration | 613 B | — | | text_encoder/config.json | Configuration | 585 B | — | | text_encoder_2/config.json | Configuration | 595 B | — | | tokenizer/special_tokens_map.json | Configuration | 472 B | — | | tokenizer_2/special_tokens_map.json | Configuration | 460 B | — | | unet/config.json | Configuration | 1.8 KB | — | | vae/config.json | Configuration | 764 B | — | | README.md | Documentation | 16.9 KB | — | | (OnomaAI)Official Description_Feb,12,2025.pdf | Other | 390.4 KB | 4dd591d2fb92 | | Illustrious Technical Report.pdf | Other | 235.9 MB | 8027d338f6cf | | TERM_OF_USE | Other | 4.3 KB | — | | .gitattributes | Repository | 1.7 KB | — | | tokenizer/merges.txt | Tokenizer | 524.6 KB | — | | tokenizer/tokenizer_config.json | Tokenizer | 704 B | — | | tokenizer/vocab.json | Tokenizer | 1.1 MB | — | | tokenizer_2/merges.txt | Tokenizer | 524.6 KB | — | | tokenizer_2/tokenizer_config.json | Tokenizer | 855 B | — | | tokenizer_2/vocab.json | Tokenizer | 1.1 MB | — | ## License and Download License other Access Open weights, no gate Download size 34.7 GB [Download from OnomaAI](https://huggingface.co/OnomaAIResearch/Illustrious-xl-early-release-v0) Released by OnomaAI through its official repository on Hugging Face. ## Built From - Derived from KBlueLeaf/kohaku-xl-beta5 - Described by arXiv:2409.19946 ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 34.7 GB | | 16-bit | 5.1 GB | | 8-bit | 2.6 GB | | 4-bit | 1.3 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Built on This Model - Derived from[amanatsu-illustrious-v11-sdxl](https://savrn.com/models/amanatsu-illustrious-v11-sdxl) - Merged from[janku-v5-nsfw-trained-noobai-rou-wei-illustrious-xl-v50-sdxl](https://savrn.com/models/janku-v5-nsfw-trained-noobai-rou-wei-illustrious-xl-v50-sdxl) - Derived from[janku-v5-nsfw-trained-noobai-rou-wei-illustrious-xl-v50-sdxl](https://savrn.com/models/janku-v5-nsfw-trained-noobai-rou-wei-illustrious-xl-v50-sdxl) - Derived from[diving-illustrious-real-asian-v50-sdxl](https://savrn.com/models/diving-illustrious-real-asian-v50-sdxl) - Quantized from[illustrious-xl-unet-gguf](https://savrn.com/models/illustrious-xl-unet-gguf) - Derived from[illustrious-xl-unet-gguf](https://savrn.com/models/illustrious-xl-unet-gguf) ## Questions About Illustrious-xl-early-release-v0 ### How much GPU memory does Illustrious-xl-early-release-v0 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 Illustrious-xl-early-release-v0 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. ### What license is Illustrious-xl-early-release-v0 released under? other, as its publisher declares it. Read the license text before commercial use. ## Similar Models Model · Text to image ### [stable-diffusion-xl-base-1.0](https://savrn.com/models/stable-diffusion-xl-base-1-0) [Stability AI](https://savrn.com/model-publishers/stabilityai) 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… Open weights openrail++ 2.6B parameters diffusers [View model](https://savrn.com/models/stable-diffusion-xl-base-1-0) Model · Text to image ### [sdxl-turbo](https://savrn.com/models/sdxl-turbo) [Stability AI](https://savrn.com/model-publishers/stabilityai) 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](https://savrn.com/models/sdxl-turbo) Model · Text to image ### [animagine-xl-4.0](https://savrn.com/models/animagine-xl-4-0) [Cagliostro Labs](https://savrn.com/model-publishers/cagliostrolab) 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](https://savrn.com/models/animagine-xl-4-0) Model · Text to image ### [playground-v2.5-1024px-aesthetic](https://savrn.com/models/playground-v2-5-1024px-aesthetic) [Playground](https://savrn.com/model-publishers/playgroundai) 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](https://savrn.com/models/playground-v2-5-1024px-aesthetic) Model · Text to image ### [animagine-xl-3.1](https://savrn.com/models/animagine-xl-3-1) [Cagliostro Labs](https://savrn.com/model-publishers/cagliostrolab) / 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](https://savrn.com/models/animagine-xl-3-1) Model · Text to image ### [nova-furry-xl-il-v120-sdxl](https://savrn.com/models/nova-furry-xl-il-v120-sdxl) [John Smith](https://savrn.com/model-publishers/john6666) Original model is here. This model created by Crody. Open weights other 2.6B parameters diffusers [View model](https://savrn.com/models/nova-furry-xl-il-v120-sdxl) ## OnomaAI [All models and datasets](https://savrn.com/model-publishers/onomaairesearch) ## Versions - [dca0dac303e6](https://savrn.com/models/illustrious-xl-early-release-v0/versions/dca0dac303e6) · current 2026-09-18 ## Explore More - [All text to image models](https://savrn.com/models/tasks/text-to-image) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-20. - [Hugging Face record](https://huggingface.co/OnomaAIResearch/Illustrious-xl-early-release-v0) - [How the hub is built](https://savrn.com/model-hub/methodology)