Download
1 variant available
fp16 SafeTensor
Visionary.safetensors
Half precision, best balance (pruned) • 1.99 GB
Verified: 3 years ago
This checkpoint includes a config file, download and place it along side the checkpoint.
9420 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
(95)
Aug 9, 2023

300 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
2170 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
Photorealistic model merge using the amazing Juggernaut final by KandooAI as a starting point. Works well even with the relatively simple negative prompt of (3d render, painting, drawing, sketch, cartoon, comics, anime:1.5). An effective positive prompt template is something like:
RAW photo. <subject > (highly detailed skin:1.2). <setting> Sigma 85mm f/1.4, 8k uhd, dslr, soft lighting, high quality, film grain.
An amateur 35mm snapshot of <subject> (highly detailed skin:1.2). <setting>
RAW photo. <subject> (highly detailed skin:1.2). <setting>
A snapshot taken with a cell phone of <subject> (highly detailed skin:1.2). <setting>
Don't forget to download the .yaml also!
. A smiling (red haired_1.4) woman wearing a diaphanous sundress with a plunging neckline. (highly det.jpeg)