Checkpoint

MeinaMix Flat is a merge of MeinaMix V11 with helloFlatArt v1.2a.Recommended parameters:Sampler: DPM++ SDE Karras: 20 to 30 steps.Sampler: DPM++ 2M Karras: 20 to 60 steps.Sampl...

User note using other negative embedding will make the model lose quality and or make it worse, even with my own negative embedding it’s not recommended to use other negative e...

Ever been stuck in a Marriot hotel room and decided to flip through the Book of Mormon in the nightstand drawer?Now you can recreate the glory of the sequel to the New Testamen...

More previews coming soon! Also all versions have Baked VAE, FYI :)Introducing Silverstar for SD 1.5!This is an SD model that I merged for my own aesthetic goals, primarily aro...

What is this?I would describe it like so: an abnormally versatile SD 1.5 model with extensive custom training done exclusively at 1024px and higher (thanks to "bucketing"). Bui...

What is this?I would describe it like so: an abnormally versatile SD 1.5 model with extensive custom training done exclusively at 1024px and higher (thanks to "bucketing"). Bui...

How this Model was made: [timelapse]This Model was created by glitching some images created with recent djz models. Audacity was used, you can see the process above.theOvercome...

What is this?I would describe it like so: an abnormally versatile SD 1.5 model with extensive custom training done exclusively at 1024px and higher (thanks to "bucketing"). Bui...

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...

Patreonも始めました, よろしければマージモデルリリースの活動を支援して下さい！I've started a Patreon. If you'd like, please support my efforts for the release of the merge model...

TamRedux adds Sardonyx v3 over my TamRealish merges, which adds a little bit more of an anime feel. I'm an especially big fan of the heavier outlines Sardonyx contributes. My c...

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...

描述: 训练词语: 名称: mixLuoaV5_.safetensors ...

Prompt : Not use qualityNegative : (low quality, worst quality, bad quality), jpeg artifacts, text, logo, furry, signature, username, multiple views, extra mouth, extra tongue,...

This checkpoint is merged with DPO LoRA.Recommended Negative Prompt : (worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexpos...

No Baked in vaepretty bad at getting the right colors. Please forgive? 描述: 训练词语: ...

VRTZPonyDiffusion-based model.Vibrant, bold linework. Expressive characters.... 描述: 训练词语: ...

This checkpoint was created by merging KandooAi's Juggernaut XL v9 with EastmanColour Style XL. The resulting checkpoint was then remerged with EastmanColour Style XL and Fred ...

Welcome to ExactitudeThis model contains several realistic human and architecture checkpoints that I've fine tuned to narrow down look and style that outputs hyper realistic im...

The keyword for this model is 'NewCN'. This model is a fine-tuned version generated based on the stable diffusion v1.5 foundation. The image dataset consists of 150 pictures of...