Подробности
Рекомендовано
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
#Аниме
#концепция
#Мультфильм
#Cammy white
#????
#полуреалистичная
#gwendolyn tennyson
#Аниме
#концепция
#Мультфильм
#Cammy white
#????
#полуреалистичная
#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)

Просмотреть перевод

Оценки и отзывы

-- /5
0 оценок

Еще не получено достаточно оценок или комментариев

M
mm2324
11
173
Объявление
2024-04-01
Публикация модели
2023-09-28
Обновить информацию о модели
Детали модели
Тип
Checkpoint
Время публикации
2023-09-28
Базовая модель
SD 1.5
Версия введения.

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

Область действия лицензии
Источник: civitai

1. Права на репостнутые модели принадлежат оригинальным создателям.

2. Для подтверждения авторства модели создателям следует обратиться к сотрудникам SeaArt AI через официальные каналы. Нажмите, чтобы подтвердить

Диапазон лицензий на создание
Прямая трансляция
Смешение
Разрешить загрузку
Коммерческая лицензия
Сгенерированные изображения можно продавать или использовать в коммерческих целях
Разрешить перепродажу моделей или продажу после интеграции
QR Code
Скачать приложение SeaArt
Продолжайте путешествие по AI-творчеству на мобильном устройстве