Sign up free, get 10,000 credits

Starter credits added when you sign up.

Oct 23, 2026

Notice: PixAI iOS App Temporarily Unavailable on the App Store — Dear PixAI users, The PixAI iOS app is currently unavailable for search and download on the App Store. We are actively w…

SD

HosekiMix

HosekiMix - AI Model cover image

Caricato su: 26 feb 2024, 22:54
Utilizzi: 1.9k
Recensioni: No reviews
Passaggi di campionamento: 25
Metodo di campionamento: DPM++ 2M Karras
Scala CFG: 5
Negativo: (worst quality, low quality:1.4), signature, watermark, username, blurry,
Permessi: Allow image generation & sharing
Permettete agli utenti di scaricare il vostro modello
Usi commerciali

Recommended LoRAs

Detail Tweaker LoRA - AI Model cover image

LoRA utente

Detail Tweaker LoRA

EnvyBetterHands LoCon_(Beta2) - AI Model cover image

LoRA utente

EnvyBetterHands LoCon_(Beta2)

prism ray - AI Model cover image

LoRA utente

detailed anime style - AI Model cover image

LoRA utente

detailed anime style

Descrizione

https://civitai.com/models/312836

Parameters I use : Positive prompt : masterpiece, best quality

Negative prompt : (worst quality, low quality:1.4), signature, watermark, username, blurry

Sampler : DPM++2M Karras - 25 steps

CFG Scale : 5

Hiresfix : 4x-AnimeSharp-lite - 0.4 denoising

Clip Skip : 2

VAE : kl-f8-anime2

The VAE is not baked in, so you can download it or use another one if you'd prefer.

I also used the EasyNegative embedding for the negative prompt, and adetailer for more detailed faces.

The models in the merge are DivineEleganceMix (v6), YesMix (v1.5), GalenaREDUX (v2), seizaMix, AingDiffusion (v9), and Sudachi.

This is my first merge, so I'm probably going to update this at some point, let me know if there's any problems!