Checkpoint

基于光辉做底模，经过九九八十一个epoch炼制而成,Based on illustrious as the base mold, it has been refined through 9*9=81 epochs.训练须知：v1版本使用了800张经过筛选的高质量的使用...

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...

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...

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...

?SakuraMoon?Prepend prompts with: score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, {prompt}Use special tags like the base model Pony XL: 'source_pony', 'sou...

Merge from NoobAI0.75 and NoobAI0.5.Based on the comment from user bioganato.With CLIPMerge Simple on ComfyUI, I nuked the Noob0.75's clip and replaced it by the Noob0.5.Compat...

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 ...

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...

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...

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...

Dusk's Animated Nightmares"24cansoffakebeer" is yes, this model, fear not it was a back mix to 2.5 somewhere and it just looked cool and i'm bored.We're looking for more conten...

Welcome to the Magical Worldwhen your fantasy & imagination becomes reality with AIInformation about this model:This model is a trained model and a fusion model. trained wi...

Description:A Cute character design Checkpoint for detailed Anime style charactersRecommended Resources:XL_VAE_C 描述: Merge details:Checkpoint 1: CutifiedAni...

Hello. long time no see, we meet again 描述: 训练词语: ...

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...

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...

Another Furry Model... woo.A development branch of a SDXL model that hopes to eventually surpass Alpha Tango in quality and accuracy, uploaded for public use and to gather feed...

Type K: Kawaii Anime StyleThis model has a very cute anime style and produces very high quality images. No detail or quality enhancing loras needed to achieve high quality imag...

Another Furry Model... woo.A development branch of a SDXL model that hopes to eventually surpass Alpha Tango in quality and accuracy, uploaded for public use and to gather feed...

Type K: Kawaii Anime StyleThis model has a very cute anime style and produces very high quality images. No detail or quality enhancing loras needed to achieve high quality imag...