Dettagli
Raccomandazioni
Scrimblo Sauce v12.0
Scrimblo Sauce v2.0
Scrimblo Sauce v11.0
Scrimblo Sauce v4.0
Scrimblo Sauce v5.0
Scrimblo Sauce v3.0
Scrimblo Sauce v1.0
Scrimblo Sauce v9.0
Scrimblo Sauce v6.2
Scrimblo Sauce v10.0
Scrimblo Sauce v7.3
Scrimblo Sauce v8.0
Scrimblo Sauce FurryMix Forever

Scrimblo Sauce FurryMix Forever

15.4K
136
889
#Photorealistic
#Base Model
#ความเปลือยเปล่า
#Photo
#รูปร่างมนุษย์
#เฟอร์รี
#????
#Photorealistic
#Base Model
#ความเปลือยเปล่า
#Photo
#รูปร่างมนุษย์
#เฟอร์รี
#????

NEEDS THESE NEGATIVE EMBEDDINGS TO WORK!

v13.0 Out Now!

  • Parameters for generation are the same as they were for v12.0, 11.0, and v10.0!

  • Much more consistent realism through generations!

  • See version details for more info!

What it is

A furry model merge using Furtastic as a base that strives to deliver as much photorealism whilst sacrificing as little expressiveness as possible.

Recommended Settings

  • Sampler: DPM++ 2M Karras or DPM++ 2M SDE Karras

    • v9 through v13 work well with DPM++ 3M SDE Karras

  • Steps: 40-75

  • Resolution: 768x768

    • v8 and onwards can generate at 1024x1024 with stability

  • CFG Scale: 5-7, 9, 12

    • v8 likes higher CFG

  • Clip Skip: 1

    • v1 and v2 use Clip Skip 2

  • Hires Fix: 5 steps at 0.25 denoising for 2x

    • v10 is the only model friendly with Hires fix to my knowledge

    • I recommend using 4x-NMKD Superscale as the upscaler

Optional Improvements

I recommend using bad-hands-5 and Boring_e621 to improve quality. Use controlnet tiles in conjunction with UltimateSD Upscale for img2img upscaling.

CivitAI Generation Information

I just made the model available to use for CivitAI generation as someone has created versions of the negative embeddings for Furtastic. You can find that here:

https://civitai.com/models/187118?modelVersionId=210143

For best results, make sure to use all 4 of the negative embeddings in your negative prompt.

Visualizza la traduzione

Valutazioni e recensioni

-- /5
0 valutazioni

Non ancora ricevute valutazioni o commenti sufficienti

R
Refiner_Img
753
19.4K
Annuncio
2024-04-01
Pubblicare modello
2023-10-19
Aggiorna le informazioni del modello
Dettagli modello
Tipo
Checkpoint
Data di pubblicazione
2023-10-19
Modello Base
SD 1.5
Introduzione alla versione

I GOT ONE MORE IN ME. Functions similarly to v11.0 and v10.0. Capable of 1024x1024 generations. Works well with 768x768 and 640x832 generations. Generally more consistent fur quality and photorealism.

Ambito di Licenza
Model Source: civitai

1. I diritti dei modelli ripubblicati appartengono ai creatori originali.

2. I creatori originali che desiderano reclamare il proprio modello devono contattare il personale di SeaArt AI tramite canali ufficiali. Clicca per rivendicare

Ambito di Licenza di Creazione
Immagini Online
Effettua una Fusione
Consenti Download
Licenza Commerciale
Le immagini generate possono essere vendute o utilizzate per scopi commerciali
Consenti la rivendita del modello o la vendita dopo la fusione
QR Code
Scarica l'app SeaArt
Continua il tuo viaggio di creazione AI su mobile