Détails
Recommandé
v2.0
[Merge] SemiRealistic attempt 2 ((Clarity_2+Photon_1, 50/50))+((Midnight Maple, 65/35))

[Merge] SemiRealistic attempt 2 ((Clarity_2+Photon_1, 50/50))+((Midnight Maple, 65/35))

1.3K
30
162
#Anime
#Concept
#Dessin animé
#Cammy white
#????
#semi-réaliste
#gwendolyn tennyson
#Anime
#Concept
#Dessin animé
#Cammy white
#????
#semi-réaliste
#gwendolyn tennyson

Update 5:

I've been using the negative embeds wrong this entire time! Not sure if it's mistranslation with Draw Things. I will be updating the sample images to reflect the difference, some may not translate well. Hence the new sample images seed's. Cfg at 6.5? Maybe not for future sample images.

The second and fourth images were rendered with CFG at 6.5. Didn't know the site was missing decimal values until I was uploading them. New image with open pose in second slide, CFG at 6.5 from here on?

Update 4:

Thanks to the review from AIArtjak, I was inspired to apply a lora from their review in the new headline images. As well apply a lora I kept seeing, "LowRA". Also applying a less is more approach when comes to the negative prompts. This merge seems to be at it's best, with other resources from the community. I'm all for that! I also wanted a redo of that Gwen image, just to make sure it wasn't a fluke.

Update 3:

Shiny skin in the negative prompt is more of a preference, the most recent renders don't have it. I tried to make sense of the shinier skin, like they're outside in the sun or sweaty after a workout for example. It still works pretty well, despite the lack of resources openly available on civitai. The site's create now option, is a joy to tinker with.

Update:

It's behaving a bit better now, trying to render a interesting image with open pose at 512x768. Also updating sample images to new resolution.

Loras, Embeddings and Models used:

[Character Loras]

Gwen-10:Gwendolyn Tennyson (Lucky Girl) - Ben 10 - v1.0 | Stable Diffusion LoRA | Civitai

[Loras]

skinny_new_skin:Skin & Hands (male/female) from Polyhedron - v1.1 | Stable Diffusion LoRA | Civitai

detailed_eye:https://huggingface.co/casque/detailed_eye-10/tree/main

LowRA:LowRA - v2.0 | Stable Diffusion LoRA | Civitai

epi_noiseoffset:epi_noiseoffset - v2 | Stable Diffusion LoRA | Civitai

[Embeddings]

https://civitai.com/models/72437/baddream-unrealisticdream-negative-embeddings

EasyNegative - EasyNegative | Stable Diffusion Embedding | Civitai

bad_prompt_version2.pt · Nerfgun3/bad_prompt at main (huggingface.co)

Bad-Hands-5 - Bad-Hands-5 | Stable Diffusion Embedding | Civitai

[Models]

Clarity - Clarity 2 | Stable Diffusion Checkpoint | Civitai

Photon - v1 | Stable Diffusion Checkpoint | Civitai

Midnight Maple.safetensors · DrBob2142/Midnight_Mixes at main (huggingface.co)

Voir la traduction

Notes & Commentaires

-- /5
0 Notes

Pas encore reçu suffisamment d'évaluations ou de commentaires

M
mm2324
11
173
Annonce
2024-04-01
Publier un modèle
2023-09-28
Mettre à jour les informations du modèle
Détails du modèle
Type
Checkpoint
Temps de Publication
2023-09-28
Modèle Basique
SD 1.5
Introduction de version

Was the headline not enough? Hope you've a wonderful day!

Périmètre de la licence
Source: civitai

1. Modèle partagé uniquement à l'apprentissage et au partage. Droits d'auteur et interprétation finale réservés à l'auteur original.

2. Auteur souhaitant revendiquer le modèle : Contactez officiellement SeaArt AI pour l'authentification. Nous protégeons les droits de chaque auteur. Cliquer pour revendiquer

Périmètre de la licence de création
Génération d'images en ligne
Effectuer une fusion
Autoriser le téléchargement
Périmètre de la licence de commerce
Les images générées peuvent être vendues ou utilisées à des fins commerciales
La revente ou la vente après fusion du modèle est autorisée.
QR Code
Télécharger l'App SeaArt
Poursuivez votre voyage de création AI sur mobile