Type | |
Stats | 16,609 793,937 |
Reviews | (2,743) |
Published | Jul 25, 2023 |
Base Model | |
Usage Tips | Clip Skip: 2 |
Hash | AutoV2 51A7154418 |
![](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/547d897e-7e9f-401d-a1ca-5606bb56cb24/original=true/547d897e-7e9f-401d-a1ca-5606bb56cb24.jpeg)
![Invader's Badge](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/afccd97d-f0b8-4f4f-bd7f-7d64b1899481/width=60/afccd97d-f0b8-4f4f-bd7f-7d64b1899481.jpeg)
![](https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/d5f25a62-432e-444a-9d9c-56be301e1b1c/original=true/user avatar decoration.jpeg)
A simple mix I've been using for a little bit. I tried to go for a flatter, more colorful style than the usual models I've been using.
I'll probably try to tweak this a bit more in the future.
This model has a baked in VAE (vae-ft-mse-840000-ema-pruned).
Parameters
Samplers: DPM++ 2M Karras/DPM++ SDE Karras/DPM++ 2M SDE Karras; 25-30 steps
CFG Scale: 6-10
Resolutions: 512 x 768 / 768 x 512
Upscalers: 4x-AnimeSharp, 4x-UltraSharp
Clip Skip: 2
Positives: masterpiece, best quality
Negatives: (worst quality, low quality:1.4), bokeh, lowres, text, signature, sketch, watermark, artist name, speech bubble, blurry
Extensions: adetailer was used to upscale/enhance faces.
This mix is primarily comprised of Animelike 2.5D, Hassaku, and Galena Redux, with a bunch of other components. Thanks to @schneed for Galena Redux.