epiCRealism XL

0
0
0
0
RealisticCGI styleStreet PhotographyGirlObject EnhanceVehicle
Atualizado recentemente: Publicado pela primeira vez:
Realistic,CGI style,Street Photography,Checkpoint,SDXLImage info
Realistic,CGI style,Street Photography,Checkpoint,SDXLImage info
Realistic,CGI style,Street Photography,Checkpoint,SDXLImage info
Realistic,CGI style,Street Photography,Checkpoint,SDXLImage info
Realistic,CGI style,Street Photography,Checkpoint,SDXLImage info
Realistic,CGI style,Street Photography,Checkpoint,SDXLImage info
Realistic,CGI style,Street Photography,Checkpoint,SDXLImage info
Realistic,CGI style,Street Photography,Checkpoint,SDXLImage info
Realistic,CGI style,Street Photography,Checkpoint,SDXLImage info
Realistic,CGI style,Street Photography,Checkpoint,SDXLImage info
Realistic,CGI style,Street Photography,Checkpoint,SDXLImage info
Realistic,CGI style,Street Photography,Checkpoint,SDXLImage info
Realistic,CGI style,Street Photography,Checkpoint,SDXLImage info
Realistic,CGI style,Street Photography,Checkpoint,SDXLImage info
Realistic,CGI style,Street Photography,Checkpoint,SDXLImage info
Realistic,CGI style,Street Photography,Checkpoint,SDXLImage info
Realistic,CGI style,Street Photography,Checkpoint,SDXLImage info
Realistic,CGI style,Street Photography,Checkpoint,SDXLImage info
Realistic,CGI style,Street Photography,Checkpoint,SDXLImage info
Realistic,CGI style,Street Photography,Checkpoint,SDXLImage info

Update2:

back on Track, i refined from V1 - probably last Version for SDXL until SD3

Keep this Secret for yourself
SDXL magic 🧙‍♂️ happens with: 30 Steps and CFG 2 🤫

Update:

since i'm low on time, i skipped training for SDXL and found the awesome Model LEOSAM's HelloWorld XL from @LEOSAM which is pretty perfect. So i decided to merge it with V1 + a WIP finetuned model around. I wouldn't say it is better in comparsion to LEOSAMs Model, so i would recommend you to use his model instead of mine. If SDXL can get better, look out for this guy 😊 Regards for all your love and support ❤

avoiding negatives can improve result on SDXL

Refined from V1 since i got a lot of responses that they don't like that leosams merge and trained with gpt4v tagged images

Discussão

Mais Popular
|
Mais Novo
Enviar
Em Breve
Download
(0.00KB)
Detalhes
Tipo
Contagem de geração online
0
Downloads
0
Parâmetros Recomendados
Sampler method
CFG
4.5
VAE
Nenhum

Galeria

Mais Popular
|
Mais Novo