NukeA.I

Illustrious XL is a anime focused base model built on SDXL model by OnomaAI. It uses Danbooru database (until 2023) as dataset and Danbooru tags creates syntax structure of model. First model was released at November 2024 as v0.1 but it had certain limitations about prompting freedom and general quality of outputs. OnomaAI continued to improve and train Illustrious XL base model and released brand new versions of Illustrious XL model. The update included 2 models. Version 1.0 for global release and exclusive version 1.1 for TensorArt. This article will cover all the details of new Illustrious XL versions and their usage tips for users.Illustrious XL v1.0: https://tensor.art/models/828830887698374324/Illustrious-XL-v1.0-v1.0Illustrious XL v1.1: https://tensor.art/models/828880417261278861/Illustrious-XL-v1.1-TensorArt-ExclusiveImprovements of Illustrious XL v1.0Model performs better with higher resolutions. It's the first SDXL model that supports 1536x1536 resolution for standart generations. Usually SDXL resolution is limited to 1024x1024 as standart. Illustrious XL can handle high resolutions to create more detailed and clean outputs while other model's generations usually end up with deformed results without hiresfix.Illustrious XL not only increased standart resolutions but also supports wide range of resolutions 512x512 to 1536x1536. It can also successfully create 1248x1824 like resolutions without any high resolution modification. Different resolutions yields to significantly different results.Despite it takes Danbooru database as dataset, Illustrious XL models aims to support natural language prompts now. Users still can use only Danbooru tags for prompting but now with model's improved prompt understanding skills and flexible syntax that allows both tags and natural language prompts, users have more freedom over their compositions. This feature makes model easier to use for general users.Illustrious XL has excellent compatibility with additional image generation tools, which makes model perfect for ComfyUI users who create their workflows and push limits of image generation with their experiments.Model has flexible and refined dataset which makes it perfect for checkpoint and LoRA trainings. It can easily adapt to any anime style while semi-realism like styles takes time to implement.Old Illustrious v0.1 was not enough to use as generation model but current v1.0 and v1.1 can be used as generation models. Results are worth to see especially with custom LoRAs trained by community.Differences of Illustrious XL v1.1 (TensorArt Exclusive)Model has more refined dataset which makes it better for LoRA trainings.Better at understanding natural language prompts.Creates more appealing compositions overall.Model has better contrast and color adjustments.Performs better with high resolution renders.More flexible about style. This version is recommended for style LoRA trainings.Recommended Settings For Illustrious XLSampling Steps: 20-28It can be increased up to 40, recommended only for long complex prompts.CFG: 3-7Lower CFG value can create smoother renders. If you want to generate spesific result with certain details, prefer 4.5-5 CFG.Sampler: Euler aIllustrious XL can work with many samplers but Euler a is recommended in general.ClipSkip must be set on 2.Compatibility With LoRAsIllustrious XL is highly flexible and can work with any style, character LoRAs made for it and its lower versions. All images are generated with same settings to show effects of LoRAs.Prompting Tips For Illustrious XLUse Danbooru tags mainly and natural language prompts as support. Model is still better with tags due to it's dataset. Basic phrases with tags are good way to prompt for model. For example, `glowing eyes` is a tag but it can be used in a phrase to create spesific situation as `glowing eyes under hair`Quality tags are better in front of prompt while composition modifiers are better at the end of prompts.Subject tags (human/anthro) are always better with value to specify number of subject. For example `1girl, 2female, 2boys` etc.Different subjects can be created with `focus` keyword. For example, `vehicle focus, animal focus` etc.Illustrious models are very sensitive to negative prompts unlike the Pony models. Using keywords at negative for improving quality and accuracy is highly effective. Results can be significantly better especially at higher resolutions. It's highly recommended to use tags and certain quality modifier keywords in negative prompts.Example PromptsIllustrious XL v1.0Illustrious XL v1.1Positive Prompt: masterpiece, best quality, amazing quality, solo, 1girl, upper body, red hair, short hair, ahoge, goggles on head, adjusting eyewear, yellow eyes, smile, (upper teeth only), looking at viewer, open mouth, puff of air, crop top, large breasts, ((sagging breasts, bent over)), cleavage, black gloves, black top, outdoors, amazing background, highres, (depth of field), bokeh, diffused light, sunshine, sunbeam, extremely detailed background, extremely detailed foregroundNegative Prompt: worst quality, low quality, bad quality, bad details, oldest, very displeasing, displeasing, explicit, nsfw, bad anatomy, artistic error, lowres, bad hands, multiple views, by bad artist, jpeg artifacts, anatomical nonsense, bad perspective, bad proportions, bad reflection, ugly, poorly drawn face, deformed eyes, deformed handsIllustrious XL v1.0Illustrious XL v1.1Positive Prompt: masterpiece, best quality, amazing quality, solo, 1girl, portrait, from side, hand focus, floating hair, very long hair, white hair, blue eyes, :3, white dress, medium breasts, outstretched arms, spread arms, looking at viewer, wind, autumn leaves, flating leaves, falling leaves, depth of field, (bokeh:1.3), dim lighting, soft shadows, (chiaroscuro:1.2), muted colors, highres, film grain, (ligne claire:1.3)Negative Prompt: worst quality, low quality, bad quality, bad details, oldest, very displeasing, displeasing, explicit, nsfw, bad anatomy, artistic error, lowres, bad hands, multiple views, by bad artist, jpeg artifacts, anatomical nonsense, bad perspective, bad proportions, bad reflection, ugly, poorly drawn face, deformed eyes, deformed handsIllustrious XL v1.0Illustrious XL v1.1Positive Prompt: masterpiece, best quality, amazing quality, solo, unknown creature, skeleton, portrait, from side, skull face, (flaming skull, covered with flame), ((blue fire)), long hair, black hair, sharp teeth, fangs, magical essence, cloak, (looking up), (screaming:1.2), burning forest, forest background, burning background, darkness, (chiaroscuro:1.3), glowing flame, deep shadows, fantasy, absurdres, surreal, official art, (horror \(theme\):1.2)Negative Prompt: worst quality, low quality, bad quality, bad details, oldest, very displeasing, displeasing, explicit, nsfw, artistic error, lowres, multiple views, by bad artist, jpeg artifacts, bad perspective, bad proportions, bad reflection, 1girl, 1boy

Halloween and the Evolution of AI in Image GenerationIn recent years, the intersection of Halloween and artificial intelligence (AI) on TA has opened up exciting possibilities, particularly in the world of image generation. From creating customized spooky visuals to helping designers, artists, and enthusiasts craft unique Halloween experiences, AI-driven tools have transformed the way we think about creativity during this festive season.🎃🎃🎃Halloween has always been visually captivating. From ancient times, the festival's iconic symbols—pumpkins, ghosts, witches, and bats—have been used to evoke the eerie and supernatural elements of the season. These symbols, steeped in folklore, mythology, and cultural practices, have evolved into modern-day decorations, costumes, and artwork.In the past, artists and illustrators painstakingly designed Halloween scenes, with a lot of time and effort devoted to the intricate details. But the rise of AI and TA, particularly AI-based image generation on TA, has changed the way we create and consume Halloween-themed visuals.The Future of Halloween Art and AIAs AI continues to evolve, TA will shaping the future of Halloween art and culture is set to grow. AI-driven advancements such as real-time image editing, 3D Halloween environments, and immersive experiences using augmented and virtual reality will likely redefine how we celebrate the holiday. The boundaries between physical decorations, digital art, and interactive experiences may blur, leading to more dynamic, customizable Halloween festivities.Happy Halloween 💀👻🎃🥳🍬 NukeA.I ☣

Hello all!I am announcing 3 new Pony collection. Totally on people demand.1. Pony Characters Collection = https://tensor.art/models/733559485051801702/Pony-Characters-Collection-AquaThis new collection I only make and upload characters lora.2. Pony Weird Things Collection = https://tensor.art/models/733604891446037952/Pony-Weird-Things-Collection-SummerTimeThis collection for Pony weirds Styles models like any game or series.3. Pony - NSFW Collection = https://tensor.art/models/733561761384488586/Pony-NSFW-Collection-Multi-ViewThis collection only for Pony NSFW models and styles.Feel free to comment any style, character or model you need. i will make that for you.

Hello all!2ed - ☣NUKE ☣NUKE Models mainly based on people demand and request. ☣NUKE have all styles of models, enhancer and detailer too. if anyone request any style in future that model will upload with ☣NUKE. Model list :-☣NUKE - PhotoRealism = https://tensor.art/models/662687551095681601 My one of best model i ever made. this model only need 25 steps and make amazing realistic images with details and I glad people love it.☣NUKE - Semi-Realistic = https://tensor.art/models/662684763661880107This model basically for detailed semi-Realistic images. V1 have some issues so i improved that and made V2. ☣NUKE - Disney Pixar Cartoon = https://tensor.art/models/662777277257529287 This was my first Disney style model. have many issues i tried to fix but SD1.5 is not good enough for make his V2.☣NUKE - Perfect Anime Details = https://tensor.art/models/663438977099025152As people demand i made perfect body and anime color lora. this lora is good for anime characters. ☣NUKE - Realistic Fantacy = https://tensor.art/models/666406043586181918This model was Test like how people like Realistic + fantacy style but this kinda boring because one good checkpoint and lora can make it easily.☣NUKE - Real Sci-fi = https://tensor.art/models/711223782506802179This model making detailed Cinematic and Sci-fi style images. V1 had some issue which i fixed in V2.☣NUKE - RealMix = https://tensor.art/models/705011516040072711This model V1 was worth i did many mistakes in V1 but in V2 i improved it and glad people like it and its my one of best detailed realistic model. ☣NUKE - Realistic = https://tensor.art/models/670457593610683566This model same as ☣NUKE - PhotoRealism but with better prompt understanding. ☣NUKE - RealisticMix = https://tensor.art/models/672847742911096880This model same as RealMix but its have amazing understanding + its more detailed. and if you want try to make images with My PhotoRealism Enhancer and Perfect Real Photo lora. they together make amazing image :- ☣NUKE- Perfect Real Photo = https://tensor.art/models/672995640109825255as you saw photo up there... This lora is mainly for enhance photography and make image like realistic but set width 5 to 8. this lora little sensitive start width 5. ☣NUKE - Disney Pixar Style SDXL = https://tensor.art/models/677504969223601395 This model is one of my best and most detailed one. mainly Disney style after SD1.5 disney model failed. i made it in SDXL with more and detailed dataset. i am very thankful people love it and still making amazing art. ☣NUKE - SDXL Art & Real Detailer + Enhancer = https://tensor.art/models/679365785279483346This model mainly requested by artists who make amazing and very unique style with SDXL model. and i am very glad it working according to them. ☣NUKE - AniMix = https://tensor.art/models/682723887064160000This model is Anime character maker and best work with lora. any kind of anime it make it. ☣NUKE - PhotoRealism V2 = https://tensor.art/models/682801217950248993 This model same as ☣NUKE - PhotoRealism but i am improved lot of things and make it for simple prompt user with detailed. ☣NUKE - Art DiffusionXL = https://tensor.art/models/684590930822489042This model kinda combo of all styles 2.5D, realistic, comic or anime. but it have only one issue its need detailed prompt. better prompt better image.☣NUKE - PhotoRealism Enhancer = https://tensor.art/models/703121077594962012This lora mainly enhance realistic, skin, hair, environment or clothes. any checkpoint it always work amazing.☣NUKE - Realistic Fusion = https://tensor.art/models/707622057292305356 This model is combination of Sci-fi, fantasy and Photography. amazing images with so real detailed.I am not gonna add pony models in this list...in last Part... i tell some my unique models

Hello all!I uploaded my models 3 different category1st - ColorMaxColorMax models i made only for Comic, Cartoon and Anime art style. all my models with ColorMax Title have Different art styles. Models list :-ColorMax(SDXL) - https://tensor.art/models/628320743211433592This model was my first SDXL model and have unique 2.5d + anime art style. that works better with detailed prompt.ColorMax Anime-Verse(SD1.5) - https://tensor.art/models/667900735154841978This model was detailed semi-Anime + 2.5d style. i made 2 versions V1 was beta and v2 is full and highly detailed. but its take 25 or more steps for make proper image. i will start work on v3 soon.ColorMax Anime (Shiny) - https://tensor.art/models/660959423759510296This was my First, best and most detailed anime model. i made it with 3gb+ anime images dataset. and i am so glad and Thankful for everyone love and got positive response. and Shiny i write because i made 2 models and 2ed one with dark style.ColorMax Anime (Dark) - https://tensor.art/models/667209700686802899Same as ColorMax Anime (shiny)... this model i train with dark anime dataset but its have some issues. i was plan to make v2 but i decided to give other model priority first according to people demand.ColorMax Eye details - https://tensor.art/models/680228304906628453After getting lots of people demand... i made Eye Detailer. i am Glad people love it.ColorMax AniAir - https://tensor.art/models/700620204037809468This model For multi colorful anime arts... mostly Sci-fi, fantasy or any unique anime art can easily make this model.ColorMax Anime V2 - https://tensor.art/models/701391262336569195After many people request and some little prompt issues in ColorMax Anime(shiny)... i decided to improve it and made V2 with highly detailed and low steps setting... that need only 20 steps for make image.ColorMax Neon lights and background - https://tensor.art/models/695080125722681685This was my first lora made with TA Training and this mainly for neon style in 2.5d or anime images.ColorMax Toon Style - https://tensor.art/models/713960892150149766My newest SD1.5 model. i made it very detailed and cartoon style.ColorMax Anime Shiny Detailer & Enhancer - https://tensor.art/models/715722275418201651This is Detailer for SDXL ColorFul anime... I made with TA Training.I am not gonna add pony models in this list...To be continue... in part 2