Checkpoint

CVS - Can Visualize StyleThis model is created purely for fun~I'm trying out something new, merging LoRA models into SD1.5 models to get better inbuilt styles and probably fix ...

This is my first model. Dreambooth trained with Kohya on a dataset of all legends and skins. I'm not very experienced so check out info in examples or try your own things.LICEN...

!!! --- best use is with dpmpp_sde or dpmpp_sde_gpu karras, not 2m or 3m, sometimes Euler a can also work --- !!!Less fantasy and cartoonish than the original, more creative th...

Hello , here a train model after a few tries , it is an evolution from me 1st train lora i put a while ago ? i will probably try again soon to further trainer better this or us...

From Google Translate来自谷歌翻译/グーグルの翻訳です/구글 번역This is an Asian model, different the previous version,This training has more image and does not include NSFW. fro...

☕ If you like what I do, buy Stoke a brew ☕Stoke SoupStoke Soup models are just ones I have put together to see how they turn out and to give you all the chance to see if there...

!!! --- best use is with dpmpp_sde or dpmpp_sde_gpu karras, not 2m or 3m, sometimes Euler a can also work --- !!!Less fantasy and cartoonish than the original, more creative th...

This is another "It's not mine but I fixed the VAE" upload.Similar-yet-different from the other kakkoii model I fixed. This one is "turbo". But its a little "thirstier" than th...

creat oil painting style creations 描述: 训练词语: ...

These "strong style" Models are intended to be merged with each other and any model for Stable Diffusion 2.1I recommend merging with 0.5 (50/50 blend) then using prompt weighti...

Simple merge between Cyberrealistic, RealisticVision and JuggernaugtXLI've had good luck with the Restart sampler40 Steps and 3 CFG 描述: 训...

This model was based on RunwayML SD 1.5 model with updated VAE.The dataset was a collaborative effort of the Stable Diffusion discord #CreatureChan channel, made of pictures fr...

This is axsUltraHorizonV21 - A new Mix collection. This series of professionally merged models is executed with careful planning and design. If the Recipe Ingredients are updat...

Recomended: Positive "Masterpiece, best quality" & negative "low quality, worst quality"If words appear use "text, watermark, words" in negativeUse "vivid color, realistic,...

This is axsUltraHorizonV21 - A new Mix collection. This series of professionally merged models is executed with careful planning and design. If the Recipe Ingredients are updat...

Matrix LightningMatrix Lightning is a merge of Mangled Merge Matrix into the SDXL Lightning 4 step model released upon request. I recommend using the following settings based o...

Merged from existing resources, focusing on realistic portrait.Sincere thanks to all great creators!Have fun! 描述: 训练词语: ...

描述: 训练词语: 名称: bianix_v10.ckpt ...

Here:Realistic V5.1 - RealisticV1.5BETA | Stable Diffusion Checkpoint | CivitaiIf not, I lost my model. It is very similar in other models. so i try it.and i have many of my re...

Hey guys!We combined a personalization model on Jennifer Lawrence and did a cool hack where we replaced the 50 class images in Dreambooth with 50 images of models from a modeli...