KenCanMixThis merged model is between 2.8D to realistic.VAE is required: <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/sd-vae-ft-mse-original">https://huggingface.co/stabilityai/sd-vae-ft-mse-original</a>Hires upscale + Dynamic Thresholding is Highly Recommended.Recommended Parameters*:Sampler: DPM++ SDE Karras, DPM++ 2M KarrasSteps: 25-50Hires upscaler: Latent (bicubic antialiased), ESRGAN_4x, R-ESRGAN 4x+Hires upscale: 1.5+Hires steps: 15+Denoising strength: 0.4-0.6CFG scale: 7-10orCFG scale: 20-30 + Dynamic ThresholdingMimic scale: 7-10Threshold percentile: 99+Mimic mode: Half Cosine UpMimic scale minimum: 3-7CFG mode: Half Cosine UpCFG scale minimum: 4-7Clip skip: 2*This is just how I use so far, feel free to play around and share with us any better one.===v.1.0===If you want Asian faces, LoRA is MUST, and the weight should be higher, try using [from:to:when] prompts. Or applying embeddings such as <a target="_blank" rel="ugc" href="https://civarchive.com/models/8109/ulzzang-6500-korean-doll-aesthetic">Ulzzang-6500</a>Credit to the authors of the following:<a target="_blank" rel="ugc" href="https://civarchive.com/models/22402/fantasticmixreal">Fantasticmix_Real</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/9052/lofi">Lofi</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/22922/lyriel">Lyriel</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/9871/chikmix">Chikmix</a>

KenCanMix

kencanmix_v10.safetensors

v1.0

Files with SHA256: 46b44aefc306fe1ae4ce35d800ac3bc19773b227783c38b34e2c503132049bdd