VAE

Trained on Anylora model.Use game resources and some fanarts as training materials.Recommend weight is 0.6 to 0.8.(Marwynn may need 0.8~1.0 to get better helmet but I don't thi...

Virile Stallion - Pony XLCome be weird with us on Discord!If you'd like to buy me a beer or coffee! ?☕V5.0 - PhotorealConfig I use:Sampling Method: DPM++ SDESampling Steps: 18 ...

XL merges from existing or paid SDXL models. Random Merges with random results. 描述: Merge with something anime-like with older version... ...

settings and stuff belowcollection of (not my) NSFW LoRas!let me know of your LoRas and i may add themDiscord: killedmyself.V13: merged v12 with a few other different mixes. Ch...

... 描述: 训练词语: 名称: ewth_v10.safetensors ...

I combining and mixed beautiful alexds9's Babes 2.0 model with epinikion's epiCRealism pure Evolution V5 which is also perfect light and detailed. For make it more interesting ...

Merger of a few different models. HyperRealism,Juggernaught,PrunedModel-2232Sha256,RealPix,PhotoRealism, and juggernaught again. Weighted sum, with a final Learned Diff for Jug...

Type M: Artistic Anime StyleThis model has an artistic style and produces very high quality images and it's good for artworks. No detail or quality enhancing loras needed to ac...

Sweet-mixSweet-mix is a text-to-image Stable Diffusion model that is mostly focused on the anime art style. The model itself is a merge of multiple other models, as i don't hav...

KL-F8 (LDM KL-8 Model)GitHub - CompVis/latent-diffusion: High-Resolution Image Synthesis with Latent Diffusion ModelsAnother exports from LDM kl-f8 I don't know same of sd1.4 m...

KL-F8 (LDM KL-8 Model)GitHub - CompVis/latent-diffusion: High-Resolution Image Synthesis with Latent Diffusion ModelsAnother exports from LDM kl-f8 I don't know same of sd1.4 m...

Un modelo que estoy creando para la universidad para proyectos personales pero si alguien le sirve el modelo adelante.Se trata de una avispa, Polistes Canandensis, una avispa q...

a model trained on visual novel dataset.will be more better on next version. i am going to train it for a week to see how it goes. for now enjoy this very first model. ...

The downloadable binary is a safetensors file for SD1.5, and it's compatible with the SD1.5 license; it's a 16ch VAE Decoder that you already know from SD3.Since the 16ch VAE i...

Neutral natural color VAE for photorealistic. Original VAE couldn't draw humans at good therefore prepared ft-mse merged VAE.Latent Diffusion Modelshttps://github.com/CompVis/l...

I made this model from various beautiful and diverse faces of Indonesian peopletry it first then see the results will definitely be satisfying and don't forget to give me appre...

Neutral natural color VAE for photorealistic. Original VAE couldn't draw humans at good therefore prepared ft-mse merged VAE.Latent Diffusion Modelshttps://github.com/CompVis/l...

The base model is https://civitai.com/models/260267/animagine-xl-v3. Do not use this lora with SD15 model. Her scar on eye can be presented with prompt ‘scar on eye’, without i...

描述: 训练词语: 名称: rmadaColdVae_v1.ckpt ...

This is the model checkpoint I trained for nearly 200 hours using a 3090. 描述: SDXL 训练词语: ...