<h1 id="heading-792">ANIMAGINE XL 2.0</h1><h3 id="heading-132">Download the model<a target="_blank" rel="ugc" href="https://huggingface.co/Linaqruf/animagine-xl-2.0/resolve/main/animagine-xl-2.0.safetensors?download=true"> here</a>, CivitAI hash checker is bad.</h3>Huggingface link: <a target="_blank" rel="ugc" href="https://huggingface.co/Linaqruf/animagine-xl-2.0">https://huggingface.co/Linaqruf/animagine-xl-2.0</a>Gradio Demo : <a target="_blank" rel="ugc" href="https://huggingface.co/spaces/Linaqruf/Animagine-XL">https://huggingface.co/spaces/Linaqruf/Animagine-XL</a> Training model is very expensive, please consider to support us at : <a target="_blank" rel="ugc" href="https://ko-fi.com/linaqruf">https://ko-fi.com/linaqruf</a><h2 id="heading-793">Overview</h2>Animagine XL 2.0 is an advanced latent text-to-image diffusion model designed to create high-resolution, detailed anime images. It's fine-tuned from Stable Diffusion XL 1.0 using a high-quality anime-style image dataset. This model, an upgrade from Animagine XL 1.0, excels in capturing the diverse and distinct styles of anime art, offering improved image quality and aesthetics.<h2 id="heading-783">Model Details</h2><ul><li>Developed by: <a target="_blank" rel="ugc" href="https://github.com/Linaqruf">Linaqruf</a></li><li>Model type: Diffusion-based text-to-image generative model</li><li>Model Description: This is a model that excels in creating detailed and high-quality anime images from text descriptions. It's fine-tuned to understand and interpret a wide range of descriptive prompts, turning them into stunning visual art.</li><li>License: <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/stable-diffusion-2/blob/main/LICENSE-MODEL">CreativeML Open RAIL++-M License</a></li><li>Finetuned from model: <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0">Stable Diffusion XL 1.0</a></li></ul><h2 id="heading-784">Gradio &amp; Colab Integration</h2>Animagine XL is accessible via <a target="_blank" rel="ugc" href="https://github.com/gradio-app/gradio">Gradio</a> Web UI and Google Colab, offering user-friendly interfaces for image generation:<ul><li>Gradio Web UI: <a target="_blank" rel="ugc" href="https://huggingface.co/spaces/Linaqruf/Animagine-XL"><img src="https://camo.githubusercontent.com/00380c35e60d6b04be65d3d94a58332be5cc93779f630bcdfc18ab9a3a7d3388/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f25463025394625413425393725323048756767696e67253230466163652d5370616365732d626c7565" alt="Open In Spaces" /></a></li><li>Google Colab: <a target="_blank" rel="ugc" href="https://colab.research.google.com/#fileId=https%3A//huggingface.co/Linaqruf/animagine-xl/blob/main/Animagine_XL_demo.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab" /></a></li></ul><h2 id="heading-785">Further information please visit <a target="_blank" rel="ugc" href="https://huggingface.co/Linaqruf/animagine-xl-2.0/">Official Repository</a> at Huggingface</h2><h3 id="heading-786"></h3>

Animagine XL (legacy)

animagineXLLegacy_v10.safetensors

Animagine XL

v1.0

v2.0

OverviewAnimagine XL is a high-resolution, latent text-to-image diffusion model. The model has been fine-tuned using a learning rate of 4e-7 over 27000 global steps with a batch size of 16 on a curated dataset of superior-quality anime-style images. This model is derived from Stable Diffusion XL 1.0.Like other anime-style Stable Diffusion models, it also supports Danbooru tags to generate images.e.g. face focus, cute, masterpiece, best quality, 1girl, green hair, sweater, looking at viewer, upper body, beanie, outdoors, night, turtleneckFeatures<ol><li>High-Resolution Images: The model trained with 1024x1024 resolution. The model is trained using&nbsp;<a target="_blank" rel="noopener nofollow" href="https://github.com/NovelAI/novelai-aspect-ratio-bucketing">NovelAI Aspect Ratio Bucketing Tool</a>&nbsp;so that it can be trained at non-square resolutions.</li><li>Anime-styled Generation: Based on given text prompts, the model can create high quality anime-styled images.</li><li>Fine-Tuned Diffusion Process: The model utilizes a fine-tuned diffusion process to ensure high quality and unique image output.</li></ol>Model Details<ul><li>Developed by:&nbsp;<a target="_blank" rel="noopener nofollow" href="https://github.com/Linaqruf">Linaqruf | </a><a target="_blank" rel="noopener noreferrer nofollow" href="https://huggingface.co/Linaqruf">https://huggingface.co/Linaqruf</a></li><li>Model type:&nbsp;Diffusion-based text-to-image generative model</li><li>Model Description:&nbsp;This is a model that can be used to generate and modify high quality anime-themed images based on text prompts.</li><li>License:&nbsp;<a target="_blank" rel="noopener nofollow" href="https://huggingface.co/stabilityai/stable-diffusion-2/blob/main/LICENSE-MODEL">CreativeML Open RAIL++-M License</a></li><li>Finetuned from model:&nbsp;<a target="_blank" rel="noopener nofollow" href="https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0">Stable Diffusion XL 1.0</a></li></ul>How to Use:<ul><li>You need to use Danbooru-style tag as <a target="_blank" rel="noopener noreferrer nofollow" href="https://huggingface.co/Linaqruf/animagine-xl/resolve/main/animagine-xl.safetensors">prom</a>pt instead of natural language, otherwise you will get realistic result instead of anime</li><li>You can use any generic negative promp<a target="_blank" rel="noopener noreferrer nofollow" href="https://huggingface.co/Linaqruf/animagine-xl/resolve/main/animagine-xl.safetensors">t or</a> use the following suggested negative prompt to guide the model towards high aesthetic generationse:</li></ul>lowres, bad anatomy, bad hands, text, <a target="_blank" rel="noopener noreferrer nofollow" href="https://huggingface.co/Linaqruf/animagine-xl/resolve/main/animagine-xl.safetensors">erro</a>r, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry<ul><li>And, the following should also be prep<a target="_blank" rel="noopener noreferrer nofollow" href="https://huggingface.co/Linaqruf/animagine-xl/resolve/main/animagine-xl.safetensors">ende</a>d to prompts to get high aesthetic results:</li></ul>masterpiece, best quality<ul><li>Use this <a target="_blank" rel="noopener noreferrer nofollow" href="https://huggingface.co/Linaqruf/animagine-xl/resolve/main/animagine-xl.safetensors">chea</a>t sheet to find the best <a target="_blank" rel="noopener noreferrer nofollow" href="https://huggingface.co/Linaqruf/animagine-xl/resolve/main/animagine-xl.safetensors">reso</a>lution:</li></ul>768 x 1344: Vertical (9:16) 915 x 1144: Portrait (4:5) 1024 x 1024: Square (1:1) 1182 x 886: Photo (4:3) 1254 x 836: Landscape (3:2) 1365 x 768: Widescreen (16:9) 1564 x 670: Cinematic (21:9)

Files with SHA256: 6f4f816f9d59295208d1136b7293ad3f7cc6b42b1e72cc5e5b2c5c728d8eeaa2