SDXL
Raehoshi Illust XLan enhanced iteration built upon the Illustrious XL model. It aims to elevate the visual style by addressing some of the limitations in the original, such as oversaturation and artifact noise. While these issues are not entirely eliminated, noticeable improvements have been made. The goal is to deliver a more polished, balanced output while staying true to the strengths of the base model.Why Early Access?Early access helps keep the project going. I don’t have my own GPU, so all training is done through rented cloud GPUs and that gets pretty expensive. By getting early access, you’re directly supporting the development of my models and helping me keep improving them. If you'd like to support me further, you can also buy me a coffee on Ko-fi! Every bit of help means a lot and keeps the future updates coming.Recommended settingPositive prompt :masterpiece, best quality, absurdresNegative prompt :bad quality, worst quality, ugly, sketch, multiple views, bad anatomy, bad hands, signature, watermarkSteps : 25+CFG : 5-7Sampler : euler a or dpm++2m karrasStandard resolution :832 x 1216, 1216 x 832, 1152 x 896, 896 x 1152, 1344 x 768, 768 x 1344, 1024 x 1024High resolution :1024 x 1536, 896 x 1536, 1536 x 1024, 1536 x 896Hires.fix Setting:Upscaler : 4x Foolhardy RemacriHires step : 10-15Denoise : 0.1-0.3Special TagsQuality Tags:masterpiecebest qualitygood qualityaverage qualitybad qualityworst qualityRating Tags:safesensitivensfwnsfw, explicitTraining DetailsThe model was developed using a two-stage fine-tuning process. In Stage 1, new series and characters were introduced into the model. Stage 2 focused on fixing issues and enhancing the overall style for improved output.Stage 1Dataset : v1-31k, v2-37k, v3-34k, v4-60k, v5_v5.1-18k, v6-15k, v7-39k, v8-41k, v9-30kHardware : 2x A100 80gb, v3, v4, v5, v5.1-2x H100 80gb, v7,v8-RTX PRO 6000Batch size : 32Gradient accumulation steps : 2Learning rate : 6e-6Text encoder : 3e-6Epoch : 15Stage 2Dataset : v1-2.5k, v2 and v3-2.3k, v4-2.5k, v5-2k, v5.1-1.8k, v6-1.5k, v7-1.7k, v7.1,v8-4.1k, v9-1.9kHardware : 1x A100 80gb, v7_v7.1,v8-RTX PRO 6000Batch size : 48Gradient accumulation steps : 1Learning rate : 3e-6, v5.1-2.5e-6, v6-adaptiveText encoder : disableEpoch : 15List of New Series/Characters Trained:Zenless Zone ZeroWuthering WavesHonkai: Star RailGenshin ImpactArknight: EndfieldUmamusumeAzur LaneArknightsFate/GODandadanMake heroine ga oo sugiruKusuriya no HotorigotoHololive from justice and dev isIndie Vtuber Dooby, Yuuki Sakuna, Nimi Nightmare, and S***100 girlfriends who really love youHaite kudasai takamine-sanAlina cloverNikke: bready and little mermaidKpop Demon HuntersFull character list are available article hereFor character trait details prompts, please refer to the Danbooru site for accurate tags and references.LicenseEach version uses a different base model, so the license may vary accordingly:v1, v2, v2.1 → based on Illustrious v0.1 → Fair AI Public License 1.0-SDv3 → based on NoobAI → Fair AI Public License 1.0-SDv4 and later → based on Illustrious v1.1 → original SDXL License with an additional if you use it in your merges or finetune, please leave a model link or mention, It's mandatory.vpred edition → based on NoobAI → Fair AI Public License 1.0-SDSpecial thanks to Joe for supporting my worksSpecial thanks to Juno for supporting my works and help me with early tester
