Checkpoint

2.5D v4.0 : Updated on 9th Nov (CityedgeMix + WAgirl2D v3.0)2D v3.0 : Updated on 4th Jun (qchan anime Mix v4 + MangetsuMRv1g(*1))2.5D v3.0 : Updated on 20th Apr (MangetsuWG3Dv2...

NoobAI+Illustrious with weight sumbasically 描述: (Illunext-V-1.1~Nooblyai~-DARE)+DARED with Noobaiv1 训练词语: ...

A mix of photo-realism and 3D to create a round/soft yet textured feel.Great for a dreamy look.Has a very flexible range for body types and poses.It's mixed with about a dozen ...

V4 has been releasedV3 has arrived, the best model.PLEASE USE THE POST BUTTON BELOW!! I WILL TIP IMAGES I LIKE!Click HERE to help me get an Nvidia Card to keep developing.V4 is...

The checkpoint type is set to "Trained" because Version 3.0 has been finetuned. Version 2.0 and 1.0 were purely done by merging checkpoints though.The baked in VAE is not in fp...

Hello. long time no see, we meet again 描述: it's new version 训练词语: ...

this is my pony variant that produces high quality and realistic outputs.Unlike other pony checkpoints, no inputs like score_9, score_8_up, score_7_up... are required.See also ...

Kaguya (輝夜姫)全般的特徴：score_ source_ 等の Positive･Negative 記述不要／ネガへ以下を記述する程度でOK！five-fingers, sticky fingers, worst quality, low quality, これら取り入...

Update: Hopefully 1.2 will work out better with more aesthetic and accurate gens counting the previous problems are mostly gone, still not the ideal version, it was a hard choi...

Modified NoobAI-XL for LoRA training.It reduces unintended style changes.This is not suitable for image generation.Recommended training parameters(sd-scripts)Dim(Rank): 4-16Alp...

This is a custom model that I merged for personal use.I don't have an exact recipe for it since I just mixed things together on a whim.The license follows the terms of Illustri...

V2.0 specific notes:See "About This Version" for more details, but I'll note here V2 is NOT a continuation of or in any way to related to V1, rather I retrained everything from...

--- v3 ---Improved skin texturesBetter environment adherenceEye ImprovementsShadow and Light improvements.--- v2 ---Improved prompt adherence (especially for non-human requests...

--- v3 ---Improved skin texturesBetter environment adherenceEye ImprovementsShadow and Light improvements.--- v2 ---Improved prompt adherence (especially for non-human requests...

Full Checkpoint with improved TE do not load additional CLIP/TESD3.5 Large with FLAN improved TEThe Full BF16 model runs at an amazing speed even on my 8GB card. It was built w...

Modified Illustrious-XL for LoRA training.It reduces unintended style changes.If you make a LoRA with this checkpoint, do not use "--noise_offset"!LoRA学習用のIllustrious-XLで...

Update: Hopefully 1.2 will work out better with more aesthetic and accurate gens counting the previous problems are mostly gone, still not the ideal version, it was a hard choi...

Full Checkpoint with improved TE do not load additional CLIP/TESD3.5 Large with FLAN improved TEThe Full BF16 model runs at an amazing speed even on my 8GB card. It was built w...

? 12/23/24: v3New version released! See version notes for change details (right column). This version is a little more stylized without going too crazy, overall seems to do a b...

Full Checkpoint with improved TE do not load additional CLIP/TESD3.5 Large with FLAN improved TEThe Full BF16 model runs at an amazing speed even on my 8GB card. It was built w...