Personal merge based on Counterfeit 3.0 I've been using for a while (You can check more polished examples on my pixiv page). Sadly, after many add-ons, the recipe is lost in time like tears in the rain.This model is focused on stylization and lora compatibility. Can't say exactly it's beginner friendly nor hard to use, you just have to prompt exactly what you want like outline, shading/lighting, and aesthetic/artist to keep consistency (by "artist" tags will give you some watermarks, so bear with it). It's pretty good for pastel/watercolor/oil painting without blowing everything up, try mixing and matching to find your preferred style!Personal recommended sampler is ancestral Euler, but other samples will also give you nice results and different styles. If your image looks fried, just crank up the steps, if it's looking like a tumor, lower the steps, pretty intuitive: CFG Scale: 5~10/ More to Less stylization and Softer to Sharper Euler/2S a Karras/Restart: &lt;25 steps / Lower denoising K Samplers: 30~40 steps / Higher denoisingUpscalers: R-ESRGAN 4x+ Anime6B/4x-AnimeSharpVAE: DogeVAE These examples are not cherry picked or inpainted, you can get better results or worse, who knows...

DogePoint

dogepoint_v10.safetensors

DogeVAE.safetensors

v1.0

FLAT v2.0

v2.0

DogeOfVenice has deleted his profile. This is a reupload of one of his models and the VAE. I don't know how to correctly add a VAE file, while selecting a file type I was only able to select "Checkpoint", so the VAE is currently labeled as "Pruned Model fp32 (159.58 MB)". The images in the showcase where made by Doge and the original upload can still be found here: <a target="_blank" rel="ugc" href="https://civarchive.com/posts/990447">https://civarchive.com/posts/990447</a>He had also made a V2.0 and a FLAT V2.0, but I do not have those models. The following is his description of the model:Personal merge based on Counterfeit 3.0 I've been using for a while (You can check more polished examples on my pixiv page). Sadly, after many add-ons, the recipe is lost in time like tears in the rain.This model is focused on stylization and lora compatibility. Can't say exactly it's beginner friendly nor hard to use, you just have to prompt exactly what you want like outline, shading/lighting, and aesthetic/artist to keep consistency (by "artist" tags will give you some watermarks, so bear with it). It's pretty good for pastel/watercolor/oil painting without blowing everything up, try mixing and matching to find your preferred style!Personal recommended sampler is ancestral Euler, but other samples will also give you nice results and different styles. If your image looks fried, just crank up the steps, if it's looking like a tumor, lower the steps, pretty intuitive:CFG Scale: 5~10/ More to Less stylization and Softer to SharperEuler/2S a Karras/Restart: &lt;25 steps / Lower denoisingK Samplers: 30~40 steps / Higher denoisingUpscalers: R-ESRGAN 4x+ Anime6B/4x-AnimeSharpVAE: DogeVAEThese examples are not cherry picked or inpainted, you can get better results or worse, who knows...

Files with SHA256: de3d3be9ebe6242c7ca6022efa218cf2cf102ffa95759ad9abeaa9480196e265