| Run Model | Run on GRAVITI Diffus |
| Model Name | KenCanMix |
| Model Type | Checkpoint |
| Base Model | SD 1.5 |
| Version Name | v1.5 |
| File Name | kencanmix_v15.safetensors |
| SHA256 | 70c012b57e |
| NSFW | False |
| Trigger Words | |
| Tags | character, photorealistic, sexy, female, cyberpunk, girls, dramatic |
| Metadata | fp = fp16 size = pruned format = SafeTensor |
| Size | 2.24 GB |
| Version Description | v1.5
Add some Asian faces. Should be compatible to the LoRAs (real or anime) but please try to find the balance on weights. |
| Source | https://civitai.com/models/34686 |
| Author | newslanding |
KenCanMix
This merged model is between 2.8D to realistic.
VAE is required: https://huggingface.co/stabilityai/sd-vae-ft-mse-original
Hires upscale + Dynamic Thresholding is Highly Recommended.
Recommended Parameters*:
Sampler: DPM++ SDE Karras, DPM++ 2M Karras
Steps: 25-50
Hires upscaler: Latent (bicubic antialiased), ESRGAN_4x, R-ESRGAN 4x+
Hires upscale: 1.5+
Hires steps: 15+
Denoising strength: 0.4-0.6
CFG scale: 7-10
or
CFG scale: 20-30 + Dynamic Thresholding
Mimic scale: 7-10
Threshold percentile: 99+
Mimic mode: Half Cosine Up
Mimic scale minimum: 3-7
CFG mode: Half Cosine Up
CFG scale minimum: 4-7
Clip 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 Ulzzang-6500
Credit to the authors of the following:
